{"total":94,"rows":[{"id":"2105.00470","title":"On Feature Decorrelation in Self-Supervised Learning","created":"2021-05-02","cited_by_count":160,"area":null},{"id":"2112.03806","title":"OOD-GNN: Out-of-Distribution Generalized Graph Neural Network","created":"2021-12-07","cited_by_count":78,"area":null},{"id":"2112.04731","title":"Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning","created":"2021-12-09","cited_by_count":49,"area":null},{"id":"2210.00226","title":"Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning","created":"2022-10-01","cited_by_count":46,"area":null},{"id":"2310.20199","title":"In Search of Lost Online Test-time Adaptation: A Survey","created":"2023-10-31","cited_by_count":44,"area":null},{"id":"2208.03160","title":"Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks","created":"2022-08-05","cited_by_count":39,"area":null},{"id":"2102.09267","title":"Sparse-Interest Network for Sequential Recommendation","created":"2021-02-18","cited_by_count":38,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2407.13987","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","created":"2024-07-19","cited_by_count":33,"area":null},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28,"area":null},{"id":"2403.19232","title":"AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search","created":"2024-03-28","cited_by_count":28,"area":null},{"id":"2106.01183","title":"A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space","created":"2021-06-02","cited_by_count":27,"area":null},{"id":"2201.07708","title":"Debiased Graph Neural Networks with Agnostic Label Selection Bias","created":"2022-01-19","cited_by_count":25,"area":null},{"id":"2404.15217","title":"Towards Large-Scale Training of Pathology Foundation Models","created":"2024-03-24","cited_by_count":23,"area":null},{"id":"2202.04812","title":"Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2206.07743","title":"Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective","created":"2022-06-15","cited_by_count":19,"area":null},{"id":"2103.05152","title":"Knowledge Evolution in Neural Networks","created":"2021-03-09","cited_by_count":18,"area":null},{"id":"2310.04867","title":"Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2211.05296","title":"Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2304.01434","title":"VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution","created":"2023-04-04","cited_by_count":17,"area":null},{"id":"2303.06484","title":"Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap","created":"2023-03-11","cited_by_count":14,"area":null},{"id":"2306.13292","title":"Variance-Covariance Regularization Improves Representation Learning","created":"2023-06-23","cited_by_count":14,"area":null},{"id":"2303.13896","title":"Regularization of polynomial networks for image recognition","created":"2023-03-24","cited_by_count":13,"area":null},{"id":"2204.11418","title":"Riemannian Hamiltonian methods for min-max optimization on manifolds","created":"2022-04-25","cited_by_count":12,"area":null},{"id":"2305.11475","title":"Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models","created":"2023-05-19","cited_by_count":12,"area":null},{"id":"2302.14460","title":"Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitis","created":"2023-02-28","cited_by_count":11,"area":null},{"id":"2306.03527","title":"Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobao","created":"2023-06-06","cited_by_count":11,"area":null},{"id":"2209.14905","title":"Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2106.04413","title":"Stochastic Whitening Batch Normalization","created":"2021-06-03","cited_by_count":9,"area":null},{"id":"2203.13203","title":"Constrained Parameter Inference as a Principle for Learning","created":"2022-03-22","cited_by_count":9,"area":null},{"id":"2306.05637","title":"On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2509.22033","title":"OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features","created":"2025-09-26","cited_by_count":8,"area":"mechinterp"},{"id":"2210.04371","title":"A Detailed Study of Interpretability of Deep Neural Network based Top Taggers","created":"2022-10-09","cited_by_count":7,"area":null},{"id":"2104.11413","title":"Unsupervised Information Obfuscation for Split Inference of Neural Networks","created":"2021-04-23","cited_by_count":5,"area":null},{"id":"2202.04629","title":"Reducing Redundancy in the Bottleneck Representation of the Autoencoders","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2206.15056","title":"FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition","created":"2022-06-30","cited_by_count":5,"area":null},{"id":"2306.00183","title":"Diffused Redundancy in Pre-trained Representations","created":"2023-05-31","cited_by_count":5,"area":"mechinterp"},{"id":"2307.04343","title":"Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2508.21421","title":"Rethinking Layer-wise Model Merging through Chain of Merges","created":"2025-08-29","cited_by_count":5,"area":null},{"id":"2106.06012","title":"Learning distinct features helps, provably","created":"2021-06-10","cited_by_count":4,"area":null},{"id":"2106.07916","title":"Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2301.01352","title":"WLD-Reg: A Data-dependent Within-layer Diversity Regularizer","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2302.14277","title":"DECOR-NET: A COVID-19 Lung Infection Segmentation Network Improved by Emphasizing Low-level Features and Decorrelating Features","created":"2023-02-28","cited_by_count":4,"area":null},{"id":"2104.06153","title":"The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks","created":"2021-04-13","cited_by_count":3,"area":null},{"id":"2203.16475","title":"Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2207.12049","title":"Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations","created":"2022-07-25","cited_by_count":3,"area":"distill"},{"id":"2208.14655","title":"XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation","created":"2022-08-31","cited_by_count":3,"area":null},{"id":"2301.03844","title":"Look Beyond Bias with Entropic Adversarial Data Augmentation","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2307.08663","title":"Quaternion Convolutional Neural Networks: Current Advances and Future Directions","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2505.14044","title":"Generalized Category Discovery via Token Manifold Capacity Learning","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2602.14283","title":"MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networking","created":"2026-02-15","cited_by_count":3,"area":null},{"id":"2111.10831","title":"Learning by Active Forgetting for Neural Networks","created":"2021-11-21","cited_by_count":2,"area":null},{"id":"2112.05827","title":"Quality-Aware Multimodal Biometric Recognition","created":"2021-12-10","cited_by_count":2,"area":null},{"id":"2304.03641","title":"A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints","created":"2023-04-07","cited_by_count":2,"area":null},{"id":"2306.10001","title":"Group Orthogonalization Regularization For Vision Models Adaptation and Robustness","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2408.15894","title":"The Role of Fibration Symmetries in Geometric Deep Learning","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2510.01172","title":"Energy-Regularized Sequential Model Editing on Hyperspheres","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2511.18567","title":"In Search of Goodness: Large Scale Benchmarking of Goodness Functions for the Forward-Forward Algorithm","created":"2025-11-23","cited_by_count":2,"area":null},{"id":"2606.11123","title":"Overcoming Rank Collapse in Feedback Alignment","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2105.09590","title":"Intra-Model Collaborative Learning of Neural Networks","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2112.06281","title":"Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer","created":"2021-12-12","cited_by_count":1,"area":null},{"id":"2208.03578","title":"Generalizability Analysis of Graph-based Trajectory Predictor with Vectorized Representation","created":"2022-08-06","cited_by_count":1,"area":null},{"id":"2310.16483","title":"Gramian Attention Heads are Strong yet Efficient Vision Learners","created":"2023-10-25","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2408.09015","title":"AdaRank: Disagreement Based Module Rank Prediction for Low-rank Adaptation","created":"2024-08-16","cited_by_count":1,"area":null},{"id":"2411.01045","title":"Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2412.05689","title":"Local Linear Convergence of Infeasible Optimization with Orthogonal Constraints","created":"2024-12-07","cited_by_count":1,"area":null},{"id":"2506.17809","title":"Flatness After All?","created":"2025-06-21","cited_by_count":1,"area":null},{"id":"2511.17724","title":"AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2602.19530","title":"ORION: ORthonormal Text Encoding for Universal VLM AdaptatION","created":"2026-02-23","cited_by_count":1,"area":"mllm"},{"id":"2602.24266","title":"Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.08374","title":"This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.19788","title":"Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentation","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"},{"id":"2101.05892","title":"A Ternary Bi-Directional LSTM Classification for Brain Activation Pattern Recognition Using fNIRS","created":"2021-01-14","cited_by_count":0,"area":null},{"id":"2112.03164","title":"Feature Disentanglement of Robot Trajectories","created":"2021-12-06","cited_by_count":0,"area":null},{"id":"2209.10865","title":"Efficient CNN with uncorrelated Bag of Features pooling","created":"2022-09-22","cited_by_count":0,"area":null},{"id":"2211.07956","title":"HGV4Risk: Hierarchical Global View-guided Sequence Representation Learning for Risk Prediction","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2306.01489","title":"On Feature Diversity in Energy-based Models","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2306.07015","title":"Combining Primal and Dual Representations in Deep Restricted Kernel Machines Classifiers","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2307.04296","title":"K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2308.04870","title":"Decorrelating neurons using persistence","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2402.18605","title":"FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2404.07083","title":"Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2411.03226","title":"Feature Map Similarity Reduction in Convolutional Neural Networks","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2411.15876","title":"DUA-D2C: Dynamic Uncertainty Aware Method for Overfitting Remediation in Deep Learning","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2505.21010","title":"Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2508.00043","title":"Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networks","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2604.25315","title":"SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.25939","title":"From Latent Space to Training Data: Explainable Specialization in Minimal MLPs","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.25989","title":"Untangling Co-Drift: Proactive Multi-Intent Failure Prediction and Root-Cause Disambiguation for Self-Driving Networks","created":"2026-07-28","cited_by_count":0,"area":"driving"},{"id":"2608.00129","title":"Progressive$^2$: A Teacher-Student Progressive Co-Evolving Knowledge Distillation Method for Substantial Model Compression","created":"2026-07-31","cited_by_count":0,"area":"distill"},{"id":"2608.04379","title":"Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.01158","title":"Superposed Latent Autoencoder","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}