{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"2008.06388","title":"Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans","created":"2020-08-14","cited_by_count":158},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"1903.09139","title":"Harmless interpolation of noisy data in regression","created":"2019-03-21","cited_by_count":121},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"1806.09471","title":"Does data interpolation contradict statistical optimality?","created":"2018-06-25","cited_by_count":95},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94},{"id":"2407.14985","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","created":"2024-07-20","cited_by_count":85},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73},{"id":"2307.09542","title":"Can Neural Network Memorization Be Localized?","created":"2023-07-18","cited_by_count":69},{"id":"2306.11074","title":"Simple and Fast Group Robustness by Automatic Feature Reweighting","created":"2023-06-19","cited_by_count":68},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54},{"id":"1912.01857","title":"Adjusting Decision Boundary for Class Imbalanced Learning","created":"2019-12-04","cited_by_count":52},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","cited_by_count":39},{"id":"2210.15031","title":"Characterizing Datapoints via Second-Split Forgetting","created":"2022-10-26","cited_by_count":37},{"id":"2209.08928","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","created":"2022-09-19","cited_by_count":34},{"id":"1902.04698","title":"Identity Crisis: Memorization and Generalization under Extreme Overparameterization","created":"2019-02-13","cited_by_count":33},{"id":"2310.00158","title":"Feedback-guided Data Synthesis for Imbalanced Classification","created":"2023-09-29","cited_by_count":33},{"id":"2212.01433","title":"Avoiding spurious correlations via logit correction","created":"2022-12-02","cited_by_count":32},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30},{"id":"2202.05189","title":"Understanding Rare Spurious Correlations in Neural Networks","created":"2022-02-10","cited_by_count":27},{"id":"2307.05831","title":"Memorization Through the Lens of Curvature of Loss Function Around Samples","created":"2023-07-11","cited_by_count":27},{"id":"2309.16748","title":"Discovering environments with XRM","created":"2023-09-28","cited_by_count":26},{"id":"2310.18555","title":"Group Robust Classification Without Any Group Information","created":"2023-10-28","cited_by_count":25},{"id":"1606.08698","title":"Reviving Threshold-Moving: a Simple Plug-in Bagging Ensemble for Binary and Multiclass Imbalanced Data","created":"2016-06-28","cited_by_count":23},{"id":"2402.09327","title":"Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization","created":"2024-02-14","cited_by_count":14},{"id":"2302.01576","title":"ResMem: Learn what you can and memorize the rest","created":"2023-02-03","cited_by_count":13},{"id":"2210.14019","title":"The Curious Case of Benign Memorization","created":"2022-10-25","cited_by_count":12},{"id":"2206.04743","title":"Strong Memory Lower Bounds for Learning Natural Models","created":"2022-06-09","cited_by_count":11},{"id":"2305.12100","title":"How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features","created":"2023-05-20","cited_by_count":11}],"next_cursor":null}