{"total":179,"rows":[{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153,"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":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93,"area":null},{"id":"2108.06227","title":"SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation","created":"2021-08-13","cited_by_count":86,"area":null},{"id":"2110.09410","title":"Exploiting Domain-Specific Features to Enhance Domain Generalization","created":"2021-10-18","cited_by_count":86,"area":null},{"id":"2306.05268","title":"Factorized Contrastive Learning: Going Beyond Multi-view Redundancy","created":"2023-06-08","cited_by_count":75,"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":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61,"area":null},{"id":"2104.10955","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","created":"2021-04-22","cited_by_count":53,"area":null},{"id":"2203.17248","title":"Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo","created":"2022-03-30","cited_by_count":52,"area":null},{"id":"2208.11296","title":"Semi-Supervised and Unsupervised Deep Visual Learning: A Survey","created":"2022-08-24","cited_by_count":52,"area":null},{"id":"2106.11232","title":"Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering","created":"2021-06-21","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":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"area":null},{"id":"2210.17444","title":"Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations","created":"2022-10-31","cited_by_count":48,"area":null},{"id":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41,"area":null},{"id":"2310.16520","title":"Towards Self-Interpretable Graph-Level Anomaly Detection","created":"2023-10-25","cited_by_count":41,"area":null},{"id":"2401.01646","title":"Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2102.03014","title":"A Variational Information Bottleneck Approach to Multi-Omics Data Integration","created":"2021-02-05","cited_by_count":40,"area":null},{"id":"2207.07635","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","created":"2022-07-15","cited_by_count":39,"area":null},{"id":"2304.04205","title":"Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification","created":"2023-04-09","cited_by_count":38,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","cited_by_count":34,"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":"2305.04477","title":"Behavior Contrastive Learning for Unsupervised Skill Discovery","created":"2023-05-08","cited_by_count":26,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2309.12458","title":"A Theory of Multimodal Learning","created":"2023-09-21","cited_by_count":25,"area":null},{"id":"2105.06138","title":"Unsupervised Hashing with Contrastive Information Bottleneck","created":"2021-05-13","cited_by_count":24,"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":"2210.08345","title":"Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations","created":"2022-10-15","cited_by_count":21,"area":null},{"id":"2408.00295","title":"Contrastive Graph Representation Learning with Adversarial Cross-view Reconstruction and Information Bottleneck","created":"2024-08-01","cited_by_count":21,"area":null},{"id":"2307.16847","title":"CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking","created":"2023-07-31","cited_by_count":19,"area":null},{"id":"2311.04193","title":"Selective Visual Representations Improve Convergence and Generalization for Embodied AI","created":"2023-11-07","cited_by_count":19,"area":null},{"id":"2204.04391","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","created":"2022-04-09","cited_by_count":17,"area":null},{"id":"2105.09401","title":"Heterogeneous Contrastive Learning","created":"2021-05-19","cited_by_count":15,"area":null},{"id":"2204.12496","title":"Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2207.10081","title":"What Do We Maximize in Self-Supervised Learning?","created":"2022-07-20","cited_by_count":15,"area":null},{"id":"2505.19996","title":"Learning Optimal Multimodal Information Bottleneck Representations","created":"2025-05-26","cited_by_count":15,"area":null},{"id":"2207.13543","title":"Abstracting Sketches through Simple Primitives","created":"2022-07-27","cited_by_count":14,"area":null},{"id":"2309.13989","title":"A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2311.01066","title":"Dynamic Multimodal Information Bottleneck for Multimodality Classification","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2410.23996","title":"An Information Criterion for Controlled Disentanglement of Multimodal Data","created":"2024-10-31","cited_by_count":14,"area":null},{"id":"2110.01280","title":"Leveraging Information Bottleneck for Scientific Document Summarization","created":"2021-10-04","cited_by_count":13,"area":null},{"id":"2506.04870","title":"Aligning Multimodal Representations through an Information Bottleneck","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2108.00045","title":"Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning","created":"2021-07-30","cited_by_count":12,"area":null},{"id":"2205.12239","title":"Gacs-Korner Common Information Variational Autoencoder","created":"2022-05-24","cited_by_count":12,"area":null},{"id":"2207.04895","title":"Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility","created":"2022-07-11","cited_by_count":12,"area":null},{"id":"2305.12743","title":"Semantic Invariant Multi-view Clustering with Fully Incomplete Information","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2409.17386","title":"Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2210.12384","title":"The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection","created":"2022-10-22","cited_by_count":11,"area":null},{"id":"2307.00761","title":"Learning Degradation-Independent Representations for Camera ISP Pipelines","created":"2023-07-03","cited_by_count":11,"area":null},{"id":"2411.09894","title":"Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2206.03601","title":"Decoupled Self-supervised Learning for Non-Homophilous Graphs","created":"2022-06-07","cited_by_count":10,"area":null},{"id":"2402.11816","title":"Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2404.17951","title":"Cauchy-Schwarz Divergence Information Bottleneck for Regression","created":"2024-04-27","cited_by_count":9,"area":null},{"id":"2105.07599","title":"Disentangled Variational Information Bottleneck for Multiview Representation Learning","created":"2021-05-17","cited_by_count":8,"area":null},{"id":"2201.06570","title":"BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR","created":"2022-01-17","cited_by_count":8,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2210.02083","title":"Multi-View Independent Component Analysis with Shared and Individual Sources","created":"2022-10-05","cited_by_count":7,"area":null},{"id":"2303.07775","title":"Data-Free Sketch-Based Image Retrieval","created":"2023-03-14","cited_by_count":7,"area":null},{"id":"2505.12473","title":"Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables","created":"2025-05-18","cited_by_count":7,"area":null},{"id":"2602.04116","title":"Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach","created":"2026-02-04","cited_by_count":7,"area":null},{"id":"2607.21973","title":"Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation","created":"2026-07-24","cited_by_count":7,"area":null},{"id":"2204.00327","title":"Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations","created":"2022-04-01","cited_by_count":6,"area":null},{"id":"2212.13726","title":"A Clustering-guided Contrastive Fusion for Multi-view Representation Learning","created":"2022-12-28","cited_by_count":6,"area":null},{"id":"2301.08970","title":"The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making","created":"2023-01-21","cited_by_count":6,"area":null},{"id":"2302.03068","title":"Evaluating Self-Supervised Learning via Risk Decomposition","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2305.03237","title":"Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2309.07200","title":"Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck","created":"2023-09-13","cited_by_count":6,"area":null},{"id":"2309.11782","title":"DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning","created":"2023-09-21","cited_by_count":6,"area":null},{"id":"2310.03311","title":"Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2505.20853","title":"Cooperation of Experts: Fusing Heterogeneous Information with Large Margin","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2110.00860","title":"Implicit and Explicit Attention for Zero-Shot Learning","created":"2021-10-02","cited_by_count":5,"area":null},{"id":"2204.10530","title":"Multi-view Information Bottleneck Without Variational Approximation","created":"2022-04-22","cited_by_count":5,"area":null},{"id":"2204.12620","title":"Rate-Constrained Remote Contextual Bandits","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2303.06329","title":"MetaViewer: Towards A Unified Multi-View Representation","created":"2023-03-11","cited_by_count":5,"area":null},{"id":"2306.09675","title":"Multi-View Class Incremental Learning","created":"2023-06-16","cited_by_count":5,"area":null},{"id":"2307.01053","title":"ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2310.06383","title":"What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?","created":"2023-10-10","cited_by_count":5,"area":null},{"id":"2403.10897","title":"Rethinking Multi-view Representation Learning via Distilled Disentangling","created":"2024-03-16","cited_by_count":5,"area":null},{"id":"2112.05787","title":"Representation Learning for Conversational Data using Discourse Mutual Information Maximization","created":"2021-12-04","cited_by_count":4,"area":null},{"id":"2112.06489","title":"Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing","created":"2021-12-13","cited_by_count":4,"area":null},{"id":"2201.08557","title":"Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective","created":"2022-01-21","cited_by_count":4,"area":null},{"id":"2206.09387","title":"Dual Representation Learning for Out-of-Distribution Detection","created":"2022-06-19","cited_by_count":4,"area":null},{"id":"2303.00002","title":"Multi-view Semantic Consistency based Information Bottleneck for Clustering","created":"2023-02-28","cited_by_count":4,"area":null},{"id":"2308.01634","title":"Disentangling Multi-view Representations Beyond Inductive Bias","created":"2023-08-03","cited_by_count":4,"area":null},{"id":"2309.04063","title":"INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2310.12431","title":"SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2310.15664","title":"Expression Syntax Information Bottleneck for Math Word Problems","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2312.07961","title":"Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2403.19078","title":"MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2406.00958","title":"Navigating Conflicting Views: Harnessing Trust for Learning","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2408.05503","title":"Disentangled Noisy Correspondence Learning","created":"2024-08-10","cited_by_count":4,"area":null},{"id":"2410.06993","title":"Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2505.12576","title":"AdaDim: Dimensionality Adaptation for SSL Representational Dynamics","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2507.09837","title":"A Pre-training Framework for Relational Data with Information-theoretic Principles","created":"2025-07-14","cited_by_count":4,"area":null},{"id":"2509.23548","title":"Disentanglement of Variations with Multimodal Generative Modeling","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2602.04920","title":"CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning","created":"2026-02-04","cited_by_count":4,"area":null}],"next_cursor":"100"}