{"list":"other","total":74,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"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":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1810.08750","title":"Learning Models with Uniform Performance via Distributionally Robust Optimization","created":"2018-10-20","cited_by_count":335},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"1602.02355","title":"Hyperparameter optimization with approximate gradient","created":"2016-02-07","cited_by_count":233},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"2002.04692","title":"Invariant Risk Minimization Games","created":"2020-02-11","cited_by_count":188},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"1610.02581","title":"Variance-based regularization with convex objectives","created":"2016-10-08","cited_by_count":155},{"id":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153},{"id":"1909.02060","title":"Distributionally Robust Language Modeling","created":"2019-09-04","cited_by_count":143},{"id":"2007.02561","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","created":"2020-07-06","cited_by_count":133},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"1705.06270","title":"A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications","created":"2017-05-17","cited_by_count":129},{"id":"1811.09358","title":"A Sufficient Condition for Convergences of Adam and RMSProp","created":"2018-11-23","cited_by_count":126},{"id":"1801.06229","title":"Anchor regression: heterogeneous data meets causality","created":"2018-01-18","cited_by_count":118},{"id":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"id":"2006.04662","title":"Rethinking Importance Weighting for Deep Learning under Distribution Shift","created":"2020-06-08","cited_by_count":93},{"id":"2105.03818","title":"Heterogeneous Risk Minimization","created":"2021-05-09","cited_by_count":90},{"id":"2106.03721","title":"OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization","created":"2021-06-07","cited_by_count":86},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75},{"id":"1911.12580","title":"Stable Learning via Sample Reweighting","created":"2019-11-28","cited_by_count":70},{"id":"2001.11713","title":"Stable Prediction with Model Misspecification and Agnostic Distribution Shift","created":"2020-01-31","cited_by_count":62},{"id":"1809.00846","title":"Towards Understanding Regularization in Batch Normalization","created":"2018-09-04","cited_by_count":56},{"id":"1711.06420","title":"Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models","created":"2017-11-17","cited_by_count":53},{"id":"2012.09382","title":"DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation","created":"2020-12-17","cited_by_count":48},{"id":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45},{"id":"2108.12178","title":"MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving","created":"2021-08-27","cited_by_count":41},{"id":"2010.04838","title":"Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator","created":"2020-10-09","cited_by_count":37},{"id":"1911.00720","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","created":"2019-11-02","cited_by_count":35},{"id":"2004.05007","title":"An Empirical Study of Invariant Risk Minimization","created":"2020-04-10","cited_by_count":35},{"id":"2106.09913","title":"Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments","created":"2021-06-18","cited_by_count":30},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30},{"id":"2108.07482","title":"G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation","created":"2021-08-17","cited_by_count":28},{"id":"2109.02038","title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","created":"2021-09-05","cited_by_count":28},{"id":"2105.12971","title":"Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation","created":"2021-05-27","cited_by_count":23},{"id":"2006.07544","title":"Risk Variance Penalization","created":"2020-06-13","cited_by_count":21},{"id":"2107.07445","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","created":"2021-07-15","cited_by_count":21},{"id":"2102.06764","title":"Technical Challenges for Training Fair Neural Networks","created":"2021-02-12","cited_by_count":20},{"id":"2205.13267","title":"Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing","created":"2022-05-26","cited_by_count":18},{"id":"2110.09940","title":"Learning Representations that Support Robust Transfer of Predictors","created":"2021-10-19","cited_by_count":17},{"id":"2203.14387","title":"Towards Domain Generalization in Object Detection","created":"2022-03-27","cited_by_count":16},{"id":"1903.03793","title":"SSN: Learning Sparse Switchable Normalization via SparsestMax","created":"2019-03-09","cited_by_count":14},{"id":"2006.10483","title":"Algorithmic Decision Making with Conditional Fairness","created":"2020-06-18","cited_by_count":14},{"id":"2205.15237","title":"VLUE: A Multi-Task Benchmark for Evaluating Vision-Language Models","created":"2022-05-30","cited_by_count":11},{"id":"2204.05941","title":"Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search","created":"2022-04-12","cited_by_count":9},{"id":"2010.01288","title":"UNISON: Unpaired Cross-lingual Image Captioning","created":"2020-10-03","cited_by_count":8},{"id":"1509.03935","title":"Markov Boundary Discovery with Ridge Regularized Linear Models","created":"2015-09-14","cited_by_count":4}],"next_cursor":null}