{"total":605,"rows":[{"id":"2101.03288","title":"How to Train Your Energy-Based Models","created":"2021-01-09","cited_by_count":274,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","cited_by_count":248,"area":null},{"id":"2102.06514","title":"Large-Scale Representation Learning on Graphs via Bootstrapping","created":"2021-02-12","cited_by_count":186,"area":null},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184,"area":null},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164,"area":null},{"id":"2110.04126","title":"3D Infomax improves GNNs for Molecular Property Prediction","created":"2021-10-08","cited_by_count":146,"area":null},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144,"area":null},{"id":"2110.06848","title":"Decoupled Contrastive Learning","created":"2021-10-13","cited_by_count":143,"area":null},{"id":"2106.12484","title":"From Canonical Correlation Analysis to Self-supervised Graph Neural Networks","created":"2021-06-23","cited_by_count":141,"area":null},{"id":"2105.07342","title":"Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive","created":"2021-05-16","cited_by_count":136,"area":null},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133,"area":null},{"id":"2109.00412","title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","created":"2021-09-01","cited_by_count":131,"area":null},{"id":"2302.14545","title":"Modern Bayesian Experimental Design","created":"2023-02-28","cited_by_count":125,"area":null},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118,"area":null},{"id":"2102.07057","title":"Learning Intents behind Interactions with Knowledge Graph for Recommendation","created":"2021-02-14","cited_by_count":94,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2205.10053","title":"What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders","created":"2022-05-20","cited_by_count":82,"area":null},{"id":"2112.08903","title":"Graph Structure Learning with Variational Information Bottleneck","created":"2021-12-16","cited_by_count":81,"area":null},{"id":"2206.07579","title":"A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions","created":"2022-06-15","cited_by_count":73,"area":null},{"id":"2304.09355","title":"To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review","created":"2023-04-19","cited_by_count":72,"area":null},{"id":"2203.07004","title":"Rethinking Minimal Sufficient Representation in Contrastive Learning","created":"2022-03-14","cited_by_count":69,"area":null},{"id":"2405.03121","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","created":"2024-05-06","cited_by_count":67,"area":null},{"id":"2106.10132","title":"VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion","created":"2021-06-18","cited_by_count":64,"area":null},{"id":"2210.06756","title":"Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features","created":"2022-10-13","cited_by_count":63,"area":null},{"id":"2111.11010","title":"Density Ratio Estimation via Infinitesimal Classification","created":"2021-11-22","cited_by_count":61,"area":null},{"id":"2206.06169","title":"Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems","created":"2022-06-13","cited_by_count":51,"area":null},{"id":"2104.02862","title":"Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification","created":"2021-04-07","cited_by_count":50,"area":null},{"id":"2204.04567","title":"Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification","created":"2022-04-09","cited_by_count":50,"area":null},{"id":"2208.04164","title":"Understanding Masked Image Modeling via Learning Occlusion Invariant Feature","created":"2022-08-08","cited_by_count":50,"area":null},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48,"area":null},{"id":"2310.08598","title":"Domain Generalization for Medical Image Analysis: A Review","created":"2023-10-05","cited_by_count":48,"area":null},{"id":"2411.01679","title":"Autoformulation of Mathematical Optimization Models Using LLMs","created":"2024-11-03","cited_by_count":48,"area":null},{"id":"2309.13378","title":"Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment","created":"2023-09-23","cited_by_count":47,"area":null},{"id":"2108.12043","title":"Learning Disentangled Representations in the Imaging Domain","created":"2021-08-26","cited_by_count":46,"area":null},{"id":"2101.04108","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","created":"2021-01-11","cited_by_count":45,"area":null},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2112.09899","title":"Improving Subgraph Recognition with Variational Graph Information Bottleneck","created":"2021-12-18","cited_by_count":45,"area":null},{"id":"2106.02881","title":"Graph Infomax Adversarial Learning for Treatment Effect Estimation with Networked Observational Data","created":"2021-06-05","cited_by_count":42,"area":null},{"id":"2310.19035","title":"Does Invariant Graph Learning via Environment Augmentation Learn Invariance?","created":"2023-10-29","cited_by_count":42,"area":null},{"id":"2404.12484","title":"Neural Methods for Amortized Inference","created":"2024-04-18","cited_by_count":39,"area":null},{"id":"2303.06818","title":"Backdoor Defense via Deconfounded Representation Learning","created":"2023-03-13","cited_by_count":38,"area":null},{"id":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2306.11078","title":"Beyond Normal: On the Evaluation of Mutual Information Estimators","created":"2023-06-19","cited_by_count":37,"area":null},{"id":"2201.12680","title":"Understanding Deep Contrastive Learning via Coordinate-wise Optimization","created":"2022-01-29","cited_by_count":35,"area":null},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35,"area":null},{"id":"2204.11028","title":"Reinforced Causal Explainer for Graph Neural Networks","created":"2022-04-23","cited_by_count":34,"area":null},{"id":"2209.06389","title":"Jointly Contrastive Representation Learning on Road Network and Trajectory","created":"2022-09-14","cited_by_count":34,"area":null},{"id":"2107.02212","title":"Featurized Density Ratio Estimation","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2108.05449","title":"Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization","created":"2021-08-11","cited_by_count":32,"area":null},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31,"area":null},{"id":"2303.03307","title":"Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2310.09031","title":"MINDE: Mutual Information Neural Diffusion Estimation","created":"2023-10-13","cited_by_count":31,"area":null},{"id":"2103.11155","title":"Recognizing Predictive Substructures with Subgraph Information Bottleneck","created":"2021-03-20","cited_by_count":28,"area":null},{"id":"2201.01702","title":"Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations","created":"2022-01-04","cited_by_count":28,"area":null},{"id":"2105.04379","title":"Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds","created":"2021-05-10","cited_by_count":27,"area":null},{"id":"2204.08585","title":"INFOrmation Prioritization through EmPOWERment in Visual Model-Based RL","created":"2022-04-18","cited_by_count":27,"area":null},{"id":"2206.15437","title":"Understanding Instance-Level Impact of Fairness Constraints","created":"2022-06-30","cited_by_count":27,"area":null},{"id":"2305.04477","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","created":"2023-05-08","cited_by_count":26,"area":null},{"id":"2309.15082","title":"RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation","created":"2023-09-26","cited_by_count":26,"area":null},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26,"area":null},{"id":"2106.02866","title":"Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning","created":"2021-06-05","cited_by_count":25,"area":null},{"id":"2106.13401","title":"Decomposed Mutual Information Estimation for Contrastive Representation Learning","created":"2021-06-25","cited_by_count":25,"area":null},{"id":"2203.15227","title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2405.13551","title":"Large Language Models are Effective Priors for Causal Graph Discovery","created":"2024-05-22","cited_by_count":24,"area":null},{"id":"2107.01475","title":"Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective","created":"2021-07-03","cited_by_count":23,"area":null},{"id":"2203.08553","title":"PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration","created":"2022-03-16","cited_by_count":23,"area":null},{"id":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"area":null},{"id":"2408.04591","title":"HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts","created":"2024-08-08","cited_by_count":23,"area":null},{"id":"2107.01152","title":"Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE","created":"2021-07-02","cited_by_count":22,"area":null},{"id":"2403.02187","title":"Mutual Information Estimation via Normalizing Flows","created":"2024-03-04","cited_by_count":22,"area":null},{"id":"2204.08504","title":"CGC: Contrastive Graph Clustering for Community Detection and Tracking","created":"2022-04-05","cited_by_count":21,"area":null},{"id":"2210.04675","title":"A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing","created":"2022-10-10","cited_by_count":21,"area":null},{"id":"2306.03301","title":"Estimating Conditional Mutual Information for Dynamic Feature Selection","created":"2023-06-05","cited_by_count":21,"area":null},{"id":"2310.11048","title":"Understanding Contrastive Learning via Distributionally Robust Optimization","created":"2023-10-17","cited_by_count":21,"area":null},{"id":"2107.10060","title":"Conditional GANs with Auxiliary Discriminative Classifier","created":"2021-07-21","cited_by_count":20,"area":null},{"id":"2110.08049","title":"Learning Semantics: An Opportunity for Effective 6G Communications","created":"2021-10-14","cited_by_count":20,"area":null},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2101.10160","title":"Measuring Dependence with Matrix-based Entropy Functional","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2108.09628","title":"DisenKGAT: Knowledge Graph Embedding with Disentangled Graph Attention Network","created":"2021-08-22","cited_by_count":19,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2201.07951","title":"Informative Pseudo-Labeling for Graph Neural Networks with Few Labels","created":"2022-01-20","cited_by_count":19,"area":null},{"id":"2207.09176","title":"Self-Supervision Can Be a Good Few-Shot Learner","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2208.02304","title":"How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?","created":"2022-08-03","cited_by_count":19,"area":null},{"id":"2209.00456","title":"ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation","created":"2022-08-27","cited_by_count":19,"area":null},{"id":"2305.08013","title":"Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression","created":"2023-05-13","cited_by_count":19,"area":null},{"id":"2102.00533","title":"Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional","created":"2021-01-31","cited_by_count":18,"area":null},{"id":"2103.08827","title":"Semi-Supervised Graph-to-Graph Translation","created":"2021-03-16","cited_by_count":18,"area":null},{"id":"2107.01131","title":"Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2303.12649","title":"MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization","created":"2023-03-22","cited_by_count":18,"area":null},{"id":"2202.01129","title":"Structure-preserving GANs","created":"2022-02-02","cited_by_count":17,"area":null},{"id":"2205.03612","title":"BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck","created":"2022-05-07","cited_by_count":17,"area":null},{"id":"2305.20025","title":"Mutual Information Estimation via $f$-Divergence and Data Derangements","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2410.22135","title":"Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation","created":"2024-10-29","cited_by_count":17,"area":null},{"id":"2103.01895","title":"Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning","created":"2021-03-02","cited_by_count":16,"area":null},{"id":"2203.04272","title":"Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models","created":"2022-03-08","cited_by_count":16,"area":null},{"id":"2301.01642","title":"CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis","created":"2023-01-04","cited_by_count":16,"area":null},{"id":"2402.00251","title":"Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning","created":"2024-02-01","cited_by_count":16,"area":null}],"next_cursor":"100"}