arXivSub Start free trial

ICML 2023 Papers with Code β€” Page 4

International Conference on Machine Learning Β· 421 papers

PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search

Haibin Wang (Alibaba Group), Xiuyu Sun (Alibaba Group)

CodeNeural Architecture SearchTransformerImage

🎯 What it does: This paper proposes PreNAS, a NAS method that first uses zero-cost proxies to filter high-quality sub-networks and then performs one-shot shared training in a limited subspace.

Probabilistic Imputation for Time-series Classification with Missing Data

SeungHyun Kim (Korea Advanced Institute of Science and Technology), Juho Lee (Korea Advanced Institute of Science and Technology)

CodeClassificationAnomaly DetectionConvolutional Neural NetworkTransformerAuto EncoderTime SeriesBiomedical DataElectronic Health Records

🎯 What it does: A probability generative framework based on the MNAR assumption, supnotMIWAE, is proposed for classifying missing data in multivariate time series, and the quality of missing value imputation is improved through ObsDropout regularization.

Probabilistic Unrolling: Scalable, Inverse-Free Maximum Likelihood Estimation for Latent Gaussian Models

Alexander Lin (Harvard University), Demba E. Ba

CodeRecommendation SystemOptimizationTabular

🎯 What it does: This paper proposes a framework called Probabilistic Unrolling to accelerate maximum likelihood estimation using gradient EM in high-dimensional latent Gaussian models (LGM). The core idea is to replace the direct inversion of the covariance matrix with Monte Carlo sampling and to solve the posterior mean and samples using iterative linear solvers (such as conjugate gradient). The iterative process is then backpropagated to obtain more accurate gradients.

Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits

Yunlong Hou (National University of Singapore), Zixin Zhong (University of Alberta)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: Proposed the 'potentially safe at any time' random combination semi-bandit problem, which requires minimizing the loss of cumulative rewards while ensuring that the variance of each step's choice does not exceed a threshold;

Progressive Purification for Instance-Dependent Partial Label Learning

Ning Xu (Southeast University), Xin Geng (Southeast University)

CodeClassificationConvolutional Neural NetworkImage

🎯 What it does: A progressive purification method named POP (PrOgressive Purification) is proposed for instance-dependent partial label learning (PLL), which gradually removes incorrect candidate labels based on the current model reliability threshold during each training epoch and retrains the model with the cleaned labels.

Proper Scoring Rules for Survival Analysis

Hiroki Yanagisawa (IBM Research)

CodeTabularTime Series

🎯 What it does: This paper conducts theoretical expansion and empirical validation of proper scoring rules in survival analysis, proving the appropriateness of four common rules (Pinball, Logarithmic, Brier, Ranked Probability Score) in survival contexts, and constructs loss functions and evaluation metrics based on these rules.

Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning

Nader Asadi (Concordia University), Eugene Belilovsky (Concordia University)

CodeClassificationKnowledge DistillationRepresentation LearningContrastive LearningImage

🎯 What it does: A continuous learning method is proposed that does not use a replay buffer, utilizing Prototype-Sample Relation Distillation (PRD) to maintain the relative similarity between old class prototypes and new task samples, thereby suppressing forgetting and enhancing adaptability.

Provable Dynamic Fusion for Low-Quality Multimodal Data

Qingyang Zhang (Tianjin University), Xi Peng (Sichuan University)

CodeClassificationRecognitionMultimodality

🎯 What it does: A dynamic multimodal fusion method QMF based on uncertainty estimation is proposed, and its superiority is proven from the perspective of generalization error theory.

Provably Convergent SchrΓΆdinger Bridge with Applications to Probabilistic Time Series Imputation

Yu Chen (Morgan Stanley), Yuriy Nevmyvaka (Morgan Stanley)

CodeRestorationData SynthesisTransformerTime SeriesSequentialBiomedical DataStochastic Differential Equation

🎯 What it does: This paper proposes an Approximate Projection-based Schrâdinger Bridge (aIPF) algorithm and provides a convergence analysis; subsequently, the algorithm is applied to probabilistic time series missing value imputation (CSBI), achieving high-quality imputation for randomly missing positions.

Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP

Jiacheng Guo (Princeton University), Xuezhou Zhang (Princeton University)

CodeOptimizationRepresentation LearningTabularBenchmark

🎯 What it does: A representation learning algorithm utilizing maximum likelihood estimation and optimistic planning is proposed to address the efficient learning and planning problem of low-rank POMDPs.

Pruning via Sparsity-indexed ODE: a Continuous Sparsity Viewpoint

Zhanfeng Mo (Nanyang Technological University), Sinno Pan

CodeOptimizationConvolutional Neural NetworkImageOrdinary Differential Equation

🎯 What it does: A continuous sparse perspective pruning framework SpODE based on sparse index ODE is proposed, along with its PSO algorithm. It utilizes the ODE of sparse evolution over time to guide the precise update of the sparse mask, achieving an efficient one-time pruning strategy.

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Stella Biderman (EleutherAI), Oskar van der Wal (Institute for Logic, Language and Computation)

CodeTransformerLarge Language ModelText

🎯 What it does: A set of 16 decoder-only autoregressive language models (Pythia) ranging in size from 70M to 12B has been constructed and publicly released, along with 154 checkpoints, a complete training data loader, and training code, supporting fine-grained experiments on training dynamics, scaling, bias, memorization, and frequency effects; case studies were also conducted on the impact of gender bias, memorization, and pre-training word frequency on task performance.

Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL

Taku Yamagata (University of Bristol), Raul Santos-Rodriguez

CodeTransformerReinforcement LearningSequential

🎯 What it does: This paper proposes an offline reinforcement learning framework called QDT, which combines Q-learning and Decision Transformer. It utilizes the value backtracking of Q-learning to re-label the return-to-go in offline data, addressing the issues of DT's lack of stitching capability and the instability of Q-learning in sparse/long-horizon tasks.

QASA: Advanced Question Answering on Scientific Articles

Yoonjoo Lee (KAIST), Moontae Lee (LG AI Research)

CodeTransformerLarge Language ModelSupervised Fine-TuningTextBenchmark

🎯 What it does: Proposed the QASA benchmark and a three-step QA method to achieve deep reasoning in scientific papers.

Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs

Lirong Wu (Westlake University), Stan Z. Li (Westlake University)

CodeKnowledge DistillationGraph Neural NetworkGraph

🎯 What it does: This paper proposes a GNN-to-MLP knowledge distillation method based on reliable knowledge points, utilizing the invariance of information entropy under noise perturbation to measure the reliability of GNN knowledge, and providing additional supervision for MLP training through reliability sampling.

Quantized Distributed Training of Large Models with Convergence Guarantees

Ilia Markov (Institute of Science and Technology Austria), Dan Alistarh (Institute of Science and Technology Austria)

CodeTransformerLarge Language ModelText

🎯 What it does: A QSDP (Quantized Sharded Data-Parallel) training framework is proposed, which can quantize weights and gradients while maintaining convergence guarantees, eliminating the communication bottleneck of FSDP and achieving efficient large-scale language model training.

RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution

Pengyi Li (Tianjin University), Xian Fu (Tianjin University)

CodeReinforcement LearningAgentic AISequentialBenchmark

🎯 What it does: Proposes the RACE framework, which combines evolutionary algorithms and multi-agent reinforcement learning to enhance collaborative learning through asymmetric representation and co-evolution.

Randomized Schur Complement Views for Graph Contrastive Learning

Vignesh Kothapalli (New York University)

CodeClassificationRepresentation LearningGraph Neural NetworkContrastive LearningGraph

🎯 What it does: A data augmentation method for graph contrastive learning based on randomized Schur complement (rLap) is proposed, utilizing random node elimination and unbiased Clique approximation to preserve the random walk probabilities of the original graph.

Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual Quality

Guy Ohayon (Technion), Tomer Michaeli (Technion)

CodeRestorationSuper ResolutionGenerative Adversarial NetworkImage

🎯 What it does: This paper discusses the advantages and disadvantages of stochastic and deterministic image recovery methods, proving that stochastic methods have theoretical advantages in consistency, perceptual quality, and robustness.

Reconstructive Neuron Pruning for Backdoor Defense

Yige Li (Xidian University), Yu-Gang Jiang (Fudan University)

CodeOptimizationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: A backdoor defense method called Reconstructive Neuron Pruning (RNP) is proposed, which combines neuron-level unlearning with filter-level recovering to expose and prune backdoor-related neurons, thereby eliminating backdoor attacks.

Reflected Diffusion Models

Aaron Lou (Stanford University), Stefano Ermon (Stanford University)

CodeGenerationData SynthesisDiffusion modelImageStochastic Differential EquationOrdinary Differential Equation

🎯 What it does: A reflection diffusion model is proposed, utilizing reflective stochastic differential equations to model in the data-supported domain;

Regret-Minimizing Double Oracle for Extensive-Form Games

Xiaohang Tang (University College London), Yaodong Yang (Peking University)

CodeOptimizationReinforcement Learning from Human FeedbackReinforcement LearningSequential

🎯 What it does: A general Regret-Minimizing Double Oracle (RMDO) framework is proposed, and based on this, a Periodic Double Oracle (PDO) is introduced to address the sample complexity issue of the double oracle method in extensive form games (EFG).

Reinforcement Learning from Passive Data via Latent Intentions

Dibya Ghosh (University of California Berkeley), Sergey Levine (University of California Berkeley)

CodeReinforcement LearningVideo

🎯 What it does: This paper proposes a method to pre-train state representations by learning latent intentions using only passive observation data (without action/reward information), and applies it to downstream reinforcement learning tasks.

Repository-Level Prompt Generation for Large Language Models of Code

Disha Shrivastava (Mila), Daniel Tarlow (McGill University)

CodeAI Code AssistantTransformerLarge Language ModelPrompt EngineeringTextRetrieval-Augmented Generation

🎯 What it does: A Repo-Level Prompt Generator (RLPG) framework is proposed, which automatically generates prompts suitable for single-line code completion by utilizing repository structure and cross-file context.

Restoration based Generative Models

Jaemoo Choi (Seoul National University), Myungjoo Kang (Seoul National University)

CodeRestorationGenerationConvolutional Neural NetworkDiffusion modelImage

🎯 What it does: A restorative generative model (RGM) is proposed through the maximum a posteriori (MAP) objective combined with implicit priors, allowing for flexible selection of the denoising process and eliminating the sampling bottleneck of traditional diffusion models.

Rethink DARTS Search Space and Renovate a New Benchmark

Jiuling Zhang (University of Chinese Academy of Sciences), Zhiming Ding (Institute of Software, Chinese Academy of Sciences)

CodeNeural Architecture SearchImageBenchmark

🎯 What it does: This paper redesigns the DARTS search space, proposing a larger and more challenging LHD space and constructing a multi-condition evaluation benchmark based on it.

Revisiting Bellman Errors for Offline Model Selection

Joshua P Zitovsky (University of North Carolina at Chapel Hill), Michael Rene Kosorok

CodeOptimizationConvolutional Neural NetworkReinforcement LearningTabularSequential

🎯 What it does: This paper studies the model selection problem in offline reinforcement learning, proposing a new estimation method based on Mean Squared Bellman Error (MSBE) and implementing the Supervised Bellman Validation (SBV) algorithm to select the optimal policy from offline data.

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

Junyuan Hong (Michigan State University), Jiayu Zhou (Michigan State University)

CodeKnowledge DistillationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: This study investigates the backdoor propagation risks of data-free knowledge distillation (data-free KD) when using contaminated teacher models and proposes a pluggable defense framework called ABD.

Revisiting Discriminative vs. Generative Classifiers: Theory and Implications

Chenyu Zheng (Renmin University of China), Jun Zhu (Tsinghua University)

CodeClassificationRepresentation LearningTransformerContrastive LearningImage

🎯 What it does: The study compares the statistical efficiency of generative naive Bayes and discriminative logistic regression classifiers in the linear evaluation of deep pre-trained models, and provides a sample complexity analysis in the case of multiple categories.

Revisiting Domain Randomization via Relaxed State-Adversarial Policy Optimization

Yun-Hsuan Lien (National Yang Ming Chiao Tung University), Yu-Shuen Wang (National Yang Ming Chiao Tung University)

CodeOptimizationReinforcement LearningSequential

🎯 What it does: This paper proposes a Relaxed Adversarial Policy Optimization (RAPPO) method, which achieves domain randomization by adding adversarial perturbations after each state transition, and simultaneously enhances both average and worst-case rewards through a bi-level optimization approach, addressing the overly conservative issues caused by traditional state adversarial methods.

Revisiting Sampling for Combinatorial Optimization

Haoran Sun (Georgia Tech), Hanjun Dai (Google Deepmind)

CodeOptimizationReinforcement LearningGraphBenchmark

🎯 What it does: An improved discrete MCMC sampling method is used to implement a training-free universal combinatorial optimization solver.

RGE: A Repulsive Graph Rectification for Node Classification via Influence

Jaeyun Song (Korea Advanced Institute of Science and Technology), Eunho Yang (AITRICS)

CodeClassificationGraph Neural NetworkGraph

🎯 What it does: This paper proposes a rejection-based edge group elimination method (RGE) that prioritizes the removal of remote edges and performs multiple rounds of retraining to reduce group effect errors, thereby improving node classification performance.

RLSbench: Domain Adaptation Under Relaxed Label Shift

Saurabh Garg (Carnegie Mellon University), Zachary Chase Lipton

CodeDomain AdaptationImageTextBenchmark

🎯 What it does: The RLSBench benchmark is proposed, evaluating 13 mainstream domain adaptation methods, exploring their performance in the 'relaxed label shift' scenario where label proportions are mismatched, and introducing a two-step meta-algorithm (pseudo-balanced resampling + post-hoc reweighting) that can be combined with most methods to significantly improve performance.

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

Louis BΓ©thune (IRIT UniversitΓ© Paul Sabatier), Andres Troya-Galvis (Thales AlΓ©nia Space)

CodeAnomaly DetectionImagePoint CloudTabular

🎯 What it does: A one-class classification method based on first-order Lipschitz neural networks learning signature distance functions (SDF) is proposed, using SDF as a normalized metric to achieve provable robustness.

Robust Subtask Learning for Compositional Generalization

Kishor Jothimurugan (University of Pennsylvania), Rajeev Alur (University of Pennsylvania)

CodeRobotic IntelligenceReinforcement Learning

🎯 What it does: Train robust subtask policies (options) to complete tasks under any subtask sequence, maximizing worst-case performance.

Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?

Ruisi Cai (University of Texas at Austin), Zhangyang Wang (University of Texas at Austin)

CodeAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: Robust Weight Signatures (RWS) are proposed, achieving lightweight, adjustable, and composable robustness patches by adding RWS to standard model weights.

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference

Pablo Lemos (Mila Quebec AI Institute), Laurence Perreault-Levasseur (Mila Quebec AI Institute)

CodeDiffusion modelGenerative Adversarial NetworkTabular

🎯 What it does: A coverage verification method based on random points (TARP) is proposed, which uses only posterior sampling to assess the accuracy of generative posterior estimators.

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

Siddharth Nayak (Massachusetts Institute of Technology), Hamsa Balakrishnan (Massachusetts Institute of Technology)

CodeRobotic IntelligenceGraph Neural NetworkReinforcement LearningAgentic AIGraph

🎯 What it does: The InforMARL framework is proposed for multi-agent navigation and collision avoidance problems, utilizing graph neural networks to aggregate local neighborhood information, thereby achieving distributed decision-making and effective collaboration under local observations.

Scalable Safe Policy Improvement via Monte Carlo Tree Search

Alberto Castellini (University of Verona), Matthijs T. J. Spaan (Delft University of Technology)

CodeOptimizationSafty and PrivacyReinforcement LearningTabular

🎯 What it does: By incorporating SPIBB constraints into MCTS, the MCTS-SPIBB algorithm is proposed to achieve online safe policy improvement.

Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation

Jeffrey Willette (KAIST), Sung Ju Hwang (KAIST)

CodeClassificationOptimizationTransformerImageText

🎯 What it does: A Universal Mini-Batch Consistent (UMBC) set encoder is proposed, along with an unbiased full gradient approximation algorithm, enabling scalable training on large-scale sets.

Scaling Laws for Generative Mixed-Modal Language Models

Armen Aghajanyan (Meta), Luke Zettlemoyer (University of Washington)

CodeGenerationData SynthesisTransformerLarge Language ModelImageTextMultimodalityAudio

🎯 What it does: This paper studies the scaling law of mixed-modal generative language models through 250+ experiments and derives an extended formula that includes modal synergy and competition.

Scaling of Class-wise Training Losses for Post-hoc Calibration

Seungjin Jung (Chung Ang University), Jongwon Choi (Chung Ang University)

CodeClassificationOptimizationConvolutional Neural NetworkImage

🎯 What it does: A post-hoc calibration method based on class-wise loss scaling is proposed, which reduces calibration error and maintains the original model accuracy by balancing the training loss across different classes.

SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching

Liren Yu (Purdue University), Xiaojun Lin (Purdue University)

CodeGraph Neural NetworkGraph

🎯 What it does: A supervised graph neural network SeedGNN is designed and implemented to match unlabeled graphs under the condition of having only a few seed nodes, and it learns to extract transferable matching knowledge from the training data.

Self-Interpretable Time Series Prediction with Counterfactual Explanations

Jingquan Yan (Rutgers University), Hao Wang (Rutgers University)

CodeExplainability and InterpretabilityAuto EncoderTime SeriesBiomedical Data

🎯 What it does: A self-explanatory time series forecasting model called CounTS is proposed, which can generate executable and causally constrained actionable counterfactual explanations while maintaining prediction accuracy.

Self-supervised learning of Split Invariant Equivariant representations

Quentin Garrido (Meta AI), Yann LeCun (New York University)

CodeRepresentation LearningContrastive LearningImageBenchmark

🎯 What it does: A self-supervised learning framework is proposed that can simultaneously learn invariant and equivariant representations of images.

Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees.

Ioannis Panageas (University of California Irvine), Volkan Cevher (Ecole Polytechnique Federale de Lausanne)

CodeOptimizationReinforcement LearningGraph

🎯 What it does: This paper proposes an online gradient descent algorithm with no regret and convergence to Nash equilibrium in a congestion game with semi-bandit feedback (SBGD-CE).

Semi-Autoregressive Energy Flows: Exploring Likelihood-Free Training of Normalizing Flows

Phillip Si (Cornell University), Volodymyr Kuleshov (Cornell University)

CodeGenerationData SynthesisFlow-based ModelImageTabular

🎯 What it does: This paper proposes a training objective based on energy scores without the need for a Jacobian determinant, and designs a semi-autoregressive energy flow model that can train reversible networks without calculating the Jacobian determinant.

Semi-Offline Reinforcement Learning for Optimized Text Generation

Changyu Chen (Renmin University of China), Rui Yan (Renmin University of China)

CodeGenerationOptimizationTransformerSupervised Fine-TuningReinforcement LearningText

🎯 What it does: A semi-offline reinforcement learning framework (semi-offline RL) is proposed, achieving a smooth transition between offline and online while balancing exploration capability and optimization cost.

Sequential Monte Carlo Learning for Time Series Structure Discovery

Feras Saad, Vikash Mansinghka

CodeOptimizationComputational EfficiencyTime Series

🎯 What it does: This paper proposes a full Bayesian structure learning framework based on Sequential Monte Carlo (SMC) and reversible MCMC for the automatic discovery of higher-order structures in time series models.

Sequential Underspecified Instrument Selection for Cause-Effect Estimation

Elisabeth Ailer (Helmholtz Munich), Niki Kilbertus (Munich Center for Machine Learning)

Code

🎯 What it does: This paper proposes a method to estimate causal effects through stepwise experiments and instrument variable selection in the case of high-dimensional processing variables where only a limited number of instrumental variables can be randomized.

Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances

Ruben Ohana (Flatiron Institute), Liva Ralaivola (Criteo AI Lab)

CodeOptimizationGenerative Adversarial NetworkImage

🎯 What it does: This paper presents a generalization error upper bound for adaptive Sliced-Wasserstein distance based on PAC-Bayesian theory, and proposes an optimization method (PAC-SW) for learning tangent distributions using this bound.

Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search

Xin Qiu (Cognizant AI Labs), Risto Miikkulainen (Cognizant AI Labs)

CodeOptimizationNeural Architecture SearchGraph

🎯 What it does: This paper proposes a crossover operator based on the Shortest Edit Path (SEP) to address the permutation problem in Neural Architecture Search (NAS).

Simple and Fast Group Robustness by Automatic Feature Reweighting

Shikai Qiu (New York University), Andrew Gordon Wilson (New York University)

CodeClassificationComputational EfficiencySupervised Fine-TuningImageText

🎯 What it does: An Automatic Feature Reweighting (AFR) method is proposed, which enhances robustness to spurious features by weighting misclassified samples and fine-tuning only the last layer of a model trained using standard ERM.

Simplified Temporal Consistency Reinforcement Learning

Yi Zhao (Aalto University), Joni Pajarinen (Aalto University)

CodeRobotic IntelligenceConvolutional Neural NetworkReinforcement LearningContrastive LearningSequential

🎯 What it does: This paper proposes a time-consistent simplified representation learning method (TCRL), which trains the encoder and hidden dynamic model using only the hidden state consistency loss, and directly trains the policy and value function on this representation, combining both model-based and model-free learning modes.

SLAMB: Accelerated Large Batch Training with Sparse Communication

Hang Xu (King Abdullah University of Science and Technology), Panos Kalnis (King Abdullah University of Science and Technology)

CodeOptimizationTransformerImageText

🎯 What it does: An optimizer named SLAMB is proposed, which combines sparse communication with large-batch training, aiming to achieve efficient distributed training on large-scale GPU clusters.

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Guangxuan Xiao (Massachusetts Institute of Technology), Song Han (Massachusetts Institute of Technology)

CodeOptimizationComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: A post-training quantization method called SmoothQuant is proposed, which can deploy large language models (such as OPT, BLOOM, GLM‑130B, MT‑NLG 530B) in INT8 weight + activation (W8A8) format without retraining the model, while maintaining accuracy close to FP16, significantly reducing memory usage and inference latency.

SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process

Zichong Li (University of Science and Technology of China), Hongyuan Zha (Chinese University of Hong Kong)

CodeTransformerScore-based ModelTextTabularTime SeriesSequentialBiomedical DataFinance Related

🎯 What it does: A Transformer Hawkes process model based on score matching (SMURF-THP) is proposed to quantify the uncertainty of event arrival times.

Social learning spontaneously emerges by searching optimal heuristics with deep reinforcement learning

Seungwoong Ha (Korea Advanced Institute of Science and Technology), Hawoong Jeong (Korea Advanced Institute of Science and Technology)

CodeOptimizationReinforcement Learning

🎯 What it does: This study uses a deep reinforcement learning model to optimize individual social learning strategies (SLS) in cooperative games and simulates the spontaneous emergence and evolution of social learning through a multidimensional NK landscape.

Solving High-Dimensional PDEs with Latent Spectral Models

Haixu Wu (Tsinghua University), Mingsheng Long (Tsinghua University)

CodeTransformerPoint CloudMeshBenchmarkPhysics Related

🎯 What it does: Latent Spectral Models (LSM) are proposed, which compress high-dimensional coordinate space into latent space through an attention-based hierarchical projection network, and then approximate the input-output mapping in the latent space using neural spectral blocks, thereby efficiently solving high-dimensional PDEs.

SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge

Mahdi Nikdan (IST Austria), Dan Alistarh (Neural Magic)

CodeComputational EfficiencyConvolutional Neural NetworkImage

🎯 What it does: This paper proposes an efficient backpropagation implementation for sparse weight networks called SparseProp;

Spatial Implicit Neural Representations for Global-Scale Species Mapping

Elijah Cole (California Institute of Technology), Oisin Mac Aodha (University of Edinburgh)

CodeTabularBenchmarkAgriculture Related

🎯 What it does: This paper utilizes Spatial Implicit Neural Representation (SINR) to jointly estimate the distribution range of approximately 47,000 species globally from a large amount of presence-only records in the iNaturalist dataset.

Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation

Qianru Zhang (University of Hong Kong), Ruihua Han (University of Hong Kong)

CodeRecommendation SystemAnomaly DetectionGraph Neural NetworkAuto EncoderContrastive LearningGraphTime Series

🎯 What it does: A self-supervised spatial-temporal graph learning framework named GraphST is proposed to learn regional embeddings under noisy and sparse urban data, which can be used for tasks such as crime prediction, traffic flow prediction, and housing price prediction.

spred: Solving L1 Penalty with SGD

Liu Ziyin (University of Tokyo), Zihao Wang (Hong Kong University of Science and Technology)

CodeCompressionOptimizationConvolutional Neural NetworkSupervised Fine-TuningImageBiomedical Data

🎯 What it does: A method is proposed to transform the L1 constraint of non-convex objectives into a differentiable problem through reparameterization (Hadamard multiplication), and directly optimize it using standard SGD (or Adam), referred to as the spred method.

SRATTA: Sample Re-ATTribution Attack of Secure Aggregation in Federated Learning.

Tanguy Marchand (Owkin Inc), Arthur Pignet (Owkin Inc)

CodeFederated LearningSafty and PrivacyAdversarial AttackConvolutional Neural NetworkImageMultimodalityBiomedical Data

🎯 What it does: In cross-device federated learning, the SRATTA attack is proposed, which can recover and classify samples to each client solely by using the aggregated model after secure aggregation, thereby breaking the privacy protection of secure aggregation.

Stable Estimation of Heterogeneous Treatment Effects

Anpeng Wu (Zhejiang University), Fei Wu (Zhejiang University)

CodeOptimizationTabular

🎯 What it does: This paper proposes the StableCFR method, which utilizes unified sampling and Ρ-greedy matching to upsample minority groups while maintaining covariate balance, thereby achieving robust heterogeneous treatment effect estimation for underrepresented populations.

Streaming Active Learning with Deep Neural Networks

Akanksha Saran (Microsoft Research), Jordan T. Ash (Microsoft Research)

CodeClassificationData-Centric LearningConvolutional Neural NetworkImage

🎯 What it does: A new batch active learning algorithm called VeSSAL is proposed, which is suitable for the application of deep neural networks in streaming environments and can immediately query labels when encountering samples.

StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes

Vaibhav Bihani (Indian Institute of Technology Delhi), N M Anoop Krishnan

CodeOptimizationGraph Neural NetworkReinforcement LearningGraph

🎯 What it does: Proposes STRIDERNET - a reinforcement learning framework based on graph neural networks to optimize atomic structures in rough energy landscapes;

Structured Cooperative Learning with Graphical Model Priors

Shuangtong Li (University of Science and Technology of China), Dacheng Tao (University of Sydney)

CodeClassificationFederated LearningGraph Neural NetworkImage

🎯 What it does: A framework for training personalized models in a decentralized environment is proposedβ€”Structured Cooperative Learning (SCooL), which automatically generates a cooperation graph through graphical model priors and collaboratively updates local models.

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

Axel Sauer (University of Tuebingen), Timo Aila (NVIDIA)

CodeGenerationData SynthesisGenerative Adversarial NetworkImageText

🎯 What it does: The StyleGAN-T model is proposed, which achieves fast and high-quality large-scale text-to-image synthesis by modifying StyleGAN-XL; multiple improvements have been made in the generator, discriminator, and training process, supporting text alignment, controllable diversity, and super-resolution.

Supervised Metric Learning to Rank for Retrieval via Contextual Similarity Optimization

Christopher Liao (Boston University), Brian Kulis (Boston University)

CodeRetrievalOptimizationContrastive LearningImage

🎯 What it does: This paper proposes a supervised metric learning loss optimized based on contextual similarity, which directly minimizes the contextual similarity between samples during training, thereby improving the ranking quality of image retrieval.

Symmetry-Aware Robot Design with Structured Subgroups

Heng Dong (Tsinghua University), Chongjie Zhang (Tsinghua University)

CodeRobotic IntelligenceGraph Neural NetworkReinforcement LearningSequential

🎯 What it does: This paper proposes a Symmetry-Aware Robot Design (SARD) framework that generates controllable and efficient robots by searching for and utilizing symmetry during the robot design process.

Synthetic data for model selection

Alon Shoshan (Amazon), Gerard Medioni

CodeData SynthesisHyperparameter SearchGenerative Adversarial NetworkImage

🎯 What it does: Using synthetic images instead of traditional validation sets to achieve model selection (including early stopping, random seed selection, and hyperparameter search)

TabLeak: Tabular Data Leakage in Federated Learning

Mark Vero (ETH Zurich), Martin Vechev (ETH Zurich)

CodeFederated LearningSafty and PrivacyTabular

🎯 What it does: A reconstruction attack method for tabular data in federated learning, called TabLeak, is proposed, which can recover a large amount of private data from gradient updates under different batch sizes and training protocols.

Task-Specific Skill Localization in Fine-tuned Language Models

Abhishek Panigrahi (Princeton University), Sanjeev Arora (Princeton University)

CodeTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringText

🎯 What it does: Research and prove that there exists a very small subset of parameters (about 0.01%) in fine-tuned language models that can retain over 95% of task performance, and propose a method for locating these 'skill' areas through model grafting.

The Benefits of Model-Based Generalization in Reinforcement Learning

Kenny John Young, JΓΌrgen Schmidhuber (International Institute of Applied Systems Analysis)

CodeReinforcement LearningTabular

🎯 What it does: Through theoretical proof (Theorem 1.1) and large-scale experiments, this paper evaluates and demonstrates the significant improvement in sampling efficiency of reinforcement learning when using learned models to generate imagined experiences in environments with factorized structures.

The Hessian perspective into the Nature of Convolutional Neural Networks

Sidak Pal Singh (ETH Zurich), Bernhard SchΓΆlkopf (MPI for Intelligent Systems)

CodeConvolutional Neural NetworkImage

🎯 What it does: This paper theoretically analyzes the structure and rank of the Hessian of the loss function of convolutional neural networks (CNNs), revealing the impact of CNN architecture on the Hessian and providing an upper bound.

The Monge Gap: A Regularizer to Learn All Transport Maps

ThΓ©o Uscidda (ENSAE), marco cuturi

CodeOptimizationDrug DiscoveryBiomedical Data

🎯 What it does: A new regularization method called Monge gap is proposed for learning optimal transport mappings under arbitrary costs without imposing strict constraints on the network structure.

The Numerical Stability of Hyperbolic Representation Learning

Gal Mishne (University of California San Diego), Sheng Yang (Harvard University)

CodeOptimizationRepresentation LearningTabularBiomedical Data

🎯 What it does: Analyzed the numerical representation capacity and gradient vanishing problem of the Poincaré ball and Lorentz model under 64-bit floating point, and proposed Euclidean parameterization to overcome these limitations.

The Power of Learned Locally Linear Models for Nonlinear Policy Optimization

Daniel Pfrommer (Massachusetts Institute of Technology), Stephen Tu (Google Brain)

CodeOptimizationRobotic IntelligenceReinforcement Learning from Human FeedbackReinforcement LearningSequential

🎯 What it does: This paper proposes a learning-based trajectory optimization algorithm that utilizes local linear models to iteratively estimate dynamics and perform iLQR-style updates in nonlinear control.

The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning

Borja RodrΓ­guez GΓ‘lvez (KTH Royal Institute of Technology), Luca Zappella (Apple)

CodeOptimizationRepresentation LearningConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper studies the impact of entropy and reconstruction on mutual information in Multi-View Self-Supervised Learning (MVSSL), proposing and validating an optimization framework based on the ER (Entropy + Reconstruction) lower bound.

The Saddle-Point Method in Differential Privacy

Wael Alghamdi (Harvard University), Lalitha Sankar (Arizona State University)

CodeOptimizationSafty and Privacy

🎯 What it does: This paper proposes a Saddle-Point Accountant (SPA) based on the saddle point method, which can accurately estimate differential privacy parameters in constant time under large compositions (many iterations);

The Value of Out-of-Distribution Data

Ashwin De Silva (Johns Hopkins University), Joshua T Vogelstein

CodeDomain AdaptationConvolutional Neural NetworkImage

🎯 What it does: The study investigates the impact of incorporating out-of-domain (OOD) samples into the training data on the generalization error of the target task, finding that the error exhibits a non-monotonic relationship with the number of OOD samples.

The Wisdom of Hindsight Makes Language Models Better Instruction Followers

Tianjun Zhang (University of California), Joseph E. Gonzalez (University of California)

CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningContrastive LearningText

🎯 What it does: A two-stage reward-free learning algorithm based on Hindsight Instruction Relabeling (HIR) is proposed, which achieves alignment by having the language model relabel instructions on its own generated outputs.

Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations

Hong-Ming Chiu (University of Illinois), Richard Y. Zhang (University of Illinois)

CodeOptimizationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: A non-convex neural network robustness provable method based on low-rank SDP constraints is proposed, overcoming the traditional LP approximation barrier.

Tighter Information-Theoretic Generalization Bounds from Supersamples

Ziqiao Wang (University of Ottawa), Yongyi Mao (University of Ottawa)

CodeContrastive LearningTabular

🎯 What it does: Under the Supersample setting, various tighter upper bounds on generalization error are proposed using information-theoretic methods such as loss difference, single loss, and Rademacher sequences.

Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering

Mingqi Yang (Dalian University of Technology), Bryan Hooi (National University of Singapore)

CodeRepresentation LearningDrug DiscoveryGraph Neural NetworkGraph

🎯 What it does: A Parameterized-(DF) framework is proposed, unifying and extending existing GNN models, achieving more flexible graph representations through learning the decomposition (D) and filtering (F) of graph matrices.

Towards Constituting Mathematical Structures for Learning to Optimize

Jialin Liu (Alibaba Group), HanQin Cai (University of Central Florida)

CodeOptimizationRecurrent Neural NetworkImageTabular

🎯 What it does: A structured learning optimizer based on mathematical conditions is proposed, with the constraint update rule in the form of a preconditioner + bias.

Towards Controlled Data Augmentations for Active Learning

Jianan Yang (Zhejiang University), Junbo Zhao

CodeClassificationData-Centric LearningImage

🎯 What it does: A proactive learning framework named CAMPAL is proposed, which can enhance the sample selection effectiveness of active learning through a controllable data augmentation strategy.

Towards Explaining Distribution Shifts

Sean Kulinski (Purdue University), David I. Inouye (Purdue University)

CodeDomain AdaptationExplainability and InterpretabilityGenerative Adversarial NetworkImageTextTabular

🎯 What it does: A distribution shift explanation framework based on interpretable transport maps is proposed, providing k-sparse, k-clustering, and interpretable mappings for image adversarial generation.

Towards Omni-generalizable Neural Methods for Vehicle Routing Problems

Jianan Zhou (Nanyang Technological University), Jie Zhang (Nanyang Technological University)

CodeOptimizationMeta LearningGraph Neural NetworkReinforcement LearningTabular

🎯 What it does: A comprehensive study on the generalization of neural methods for the vehicle routing problem in full size and distribution.

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Yulun Jiang (Γ‰cole Polytechnique FΓ©dΓ©rale de Lausanne), Sabine SΓΌsstrunk

CodeOptimizationAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: An efficient and stable adversarial training method for l1 norm perturbations, Fast-EGl 1, is proposed to address the issue of catastrophic overfitting that traditional methods face under l1 perturbations.

Towards Sustainable Learning: Coresets for Data-efficient Deep Learning

Yu Yang (University of California Los Angeles), Baharan Mirzasoleiman (University of California Los Angeles)

CodeOptimizationData-Centric LearningConvolutional Neural NetworkTransformerImageText

🎯 What it does: The CREST framework is proposed, which improves the sample efficiency and sustainability of deep learning by segmenting non-convex loss into piecewise quadratic approximations and constructing mini-batch coresets in each sub-region, dynamically updated.

Towards Understanding and Reducing Graph Structural Noise for GNNs

Mingze Dong (Yale University), Yuval Kluger (Yale University)

CodeGraph Neural NetworkGraph

🎯 What it does: A new graph structure noise assessment metric ESNR is proposed, along with a graph rearrangement framework GPS based on self-supervised graph link prediction, aimed at quantifying and reducing the negative impact of graph structure noise on the performance of Graph Neural Networks (GNNs).

TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation

Zhaoyan Liu (Layer 6 AI), Gabriel Loaiza-Ganem (Layer 6 AI)

CodeGenerationData SynthesisAuto EncoderGenerative Adversarial NetworkImageText

🎯 What it does: TR0N transforms any pre-trained unconditional generative model (such as GANs, VAEs) into a zero-shot conditional generation framework that can generate samples based on any condition (category, text, image semantics) without the need for additional data or fine-tuning.

Tractable Control for Autoregressive Language Generation

Honghua Zhang (University of California), Guy Van den Broeck (University of California)

CodeGenerationOptimizationKnowledge DistillationRecurrent Neural NetworkLarge Language ModelText

🎯 What it does: The GeLaTo framework is proposed, which combines solvable probabilistic models (such as HMM) with large-scale autoregressive language models to generate text that meets lexical constraints.

Trainability, Expressivity and Interpretability in Gated Neural ODEs

Timothy Doyeon Kim (Princeton University), Kamesh Krishnamurthy (Princeton University)

CodeExplainability and InterpretabilityComputational EfficiencyRecurrent Neural NetworkTime SeriesSequentialOrdinary Differential EquationAudio

🎯 What it does: This paper proposes and studies the Gated Neural Ordinary Differential Equation (gnODE), exploring its trainability, expressiveness, and interpretability, and conducting experimental validation on various synthetic and real datasets.

TRAK: Attributing Model Behavior at Scale

Sung Min Park (Massachusetts Institute of Technology), Aleksander Madry (Massachusetts Institute of Technology)

CodeExplainability and InterpretabilityComputational EfficiencyConvolutional Neural NetworkTransformerImageText

🎯 What it does: A data attribution method named TRAK is proposed, which can efficiently trace the sources of model predictions in large-scale non-convex models.

Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Driving

Weixin Li, Xiaodong Yang (QCraft)

CodeAutonomous DrivingOptimizationPoint Cloud

🎯 What it does: A perception assessment framework TIP based on a planning perspective is proposed, utilizing the expected utility maximization theory to map perception errors into Hilbert space and quantify their impact on autonomous driving planning decisions.

Transformed Distribution Matching for Missing Value Imputation

He Zhao (CSIRO Data61), Edwin V. Bonilla (CSIRO Data61)

CodeOptimizationData-Centric LearningFlow-based ModelTabular

🎯 What it does: In datasets with missing values, an unsupervised missing value imputation method based on distribution matching, called TDM, is proposed;

Understand and Modularize Generator Optimization in ELECTRA-style Pretraining

Chengyu Dong (University of California), Xiaodong Liu (Microsoft Research)

CodeGenerationOptimizationTransformerTextBenchmark

🎯 What it does: In ELECTRA-style pre-training, the system analyzes the impact of generator capacity on discriminator performance and proposes to control generator training by completely decoupling the optimizers of the generator and discriminator, significantly reducing the model's sensitivity to generator size and improving downstream task performance.