{"list":"other","total":119,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"1805.04049","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","created":"2018-05-10","cited_by_count":520},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"1910.03581","title":"FedMD: Heterogenous Federated Learning via Model Distillation","created":"2019-10-08","cited_by_count":459},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2004.12088","title":"SplitFed: When Federated Learning Meets Split Learning","created":"2020-04-25","cited_by_count":310},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"1811.11479","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","created":"2018-11-28","cited_by_count":243},{"id":"2106.05001","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","created":"2021-06-09","cited_by_count":241},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"1803.04765","title":"Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning","created":"2018-03-13","cited_by_count":207},{"id":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"2006.04924","title":"A Self-supervised Approach for Adversarial Robustness","created":"2020-06-08","cited_by_count":180},{"id":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"2003.08082","title":"Federated Visual Classification with Real-World Data Distribution","created":"2020-03-18","cited_by_count":128},{"id":"2203.11473","title":"Federated Class-Incremental Learning","created":"2022-03-22","cited_by_count":127},{"id":"1902.11175","title":"One-Shot Federated Learning","created":"2019-02-28","cited_by_count":125},{"id":"2110.00857","title":"FairFed: Enabling Group Fairness in Federated Learning","created":"2021-10-02","cited_by_count":118},{"id":"2009.07999","title":"Distilled One-Shot Federated Learning","created":"2020-09-17","cited_by_count":109},{"id":"2209.00189","title":"Federated Learning with Label Distribution Skew via Logits Calibration","created":"2022-09-01","cited_by_count":109},{"id":"2107.00233","title":"FedMix: Approximation of Mixup under Mean Augmented Federated Learning","created":"2021-07-01","cited_by_count":108},{"id":"2112.12371","title":"DENSE: Data-Free One-Shot Federated Learning","created":"2021-12-23","cited_by_count":100},{"id":"2106.04496","title":"Towards a Theoretical Framework of Out-of-Distribution Generalization","created":"2021-06-08","cited_by_count":94},{"id":"1912.11279","title":"Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer","created":"2019-12-24","cited_by_count":93},{"id":"2010.12050","title":"Contrastive Learning with Adversarial Examples","created":"2020-10-22","cited_by_count":91},{"id":"2103.00697","title":"Heterogeneity for the Win: One-Shot Federated Clustering","created":"2021-03-01","cited_by_count":87},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87},{"id":"2010.05273","title":"Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms","created":"2020-10-11","cited_by_count":78},{"id":"2010.01017","title":"Practical One-Shot Federated Learning for Cross-Silo Setting","created":"2020-10-02","cited_by_count":77},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75},{"id":"2101.10832","title":"Revisiting Locally Supervised Learning: an Alternative to End-to-end Training","created":"2021-01-26","cited_by_count":71},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"2212.02758","title":"Tackling Data Heterogeneity in Federated Learning with Class Prototypes","created":"2022-12-06","cited_by_count":67},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","cited_by_count":66},{"id":"2104.13417","title":"Towards Fair Federated Learning with Zero-Shot Data Augmentation","created":"2021-04-27","cited_by_count":64},{"id":"2010.16412","title":"Empirical or Invariant Risk Minimization? A Sample Complexity Perspective","created":"2020-10-30","cited_by_count":62},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62},{"id":"2006.05148","title":"XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning","created":"2020-06-09","cited_by_count":58},{"id":"2004.10342","title":"Federated Learning with Only Positive Labels","created":"2020-04-21","cited_by_count":55},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55},{"id":"2303.10058","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","created":"2023-03-17","cited_by_count":55},{"id":"2008.04489","title":"Federated Learning via Synthetic Data","created":"2020-08-11","cited_by_count":54},{"id":"2310.05077","title":"FedFed: Feature Distillation against Data Heterogeneity in Federated Learning","created":"2023-10-08","cited_by_count":54},{"id":"1906.09338","title":"G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators","created":"2019-06-21","cited_by_count":53},{"id":"2302.00903","title":"No One Left Behind: Real-World Federated Class-Incremental Learning","created":"2023-02-02","cited_by_count":53},{"id":"2206.02465","title":"Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning","created":"2022-06-06","cited_by_count":52},{"id":"2302.10429","title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","created":"2023-02-21","cited_by_count":49},{"id":"2305.11584","title":"Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape","created":"2023-05-19","cited_by_count":46},{"id":"2208.02507","title":"ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity","created":"2022-08-04","cited_by_count":45},{"id":"2004.08628","title":"Single-step Adversarial training with Dropout Scheduling","created":"2020-04-18","cited_by_count":41}],"next_cursor":"100"}