{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"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":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"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":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"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":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"1812.10352","title":"Learning Not to Learn: Training Deep Neural Networks with Biased Data","created":"2018-12-26","cited_by_count":255},{"id":"1911.11834","title":"Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation","created":"2019-11-26","cited_by_count":252},{"id":"1803.10837","title":"Learning Deep Representations with Probabilistic Knowledge Transfer","created":"2018-03-28","cited_by_count":213},{"id":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"1910.02806","title":"Learning De-biased Representations with Biased Representations","created":"2019-10-07","cited_by_count":199},{"id":"1906.10169","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","created":"2019-06-24","cited_by_count":185},{"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":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"1904.07911","title":"REPAIR: Removing Representation Bias by Dataset Resampling","created":"2019-04-16","cited_by_count":157},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"2203.14001","title":"Knowledge Distillation with the Reused Teacher Classifier","created":"2022-03-26","cited_by_count":141},{"id":"1903.06256","title":"Learning Robust Representations by Projecting Superficial Statistics Out","created":"2019-03-02","cited_by_count":123},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62},{"id":"2203.02110","title":"FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis","created":"2022-03-04","cited_by_count":59},{"id":"1907.09013","title":"Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classification","created":"2019-07-21","cited_by_count":55},{"id":"2206.10843","title":"Learning Debiased Classifier with Biased Committee","created":"2022-06-22","cited_by_count":51},{"id":"2009.14410","title":"Pruning Filter in Filter","created":"2020-09-30","cited_by_count":47},{"id":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38},{"id":"2211.02291","title":"SelecMix: Debiased Learning by Contradicting-pair Sampling","created":"2022-11-04","cited_by_count":29},{"id":"2003.06430","title":"Learning Unbiased Representations via Mutual Information Backpropagation","created":"2020-03-13","cited_by_count":25},{"id":"2106.02866","title":"Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning","created":"2021-06-05","cited_by_count":25},{"id":"2310.18555","title":"Group Robust Classification Without Any Group Information","created":"2023-10-28","cited_by_count":25},{"id":"1906.06110","title":"Towards Compact and Robust Deep Neural Networks","created":"2019-06-14","cited_by_count":23},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23},{"id":"2312.15398","title":"Fairness-Aware Structured Pruning in Transformers","created":"2023-12-24","cited_by_count":22},{"id":"2203.16540","title":"Mind the gap: Challenges of deep learning approaches to Theory of Mind","created":"2022-03-30","cited_by_count":21},{"id":"2009.09936","title":"Prune Responsibly","created":"2020-09-10","cited_by_count":20},{"id":"2001.07710","title":"An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices","created":"2020-01-20","cited_by_count":18},{"id":"2304.14252","title":"FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations","created":"2023-04-27","cited_by_count":18},{"id":"2210.05247","title":"Training Debiased Subnetworks with Contrastive Weight Pruning","created":"2022-10-11","cited_by_count":16},{"id":"2210.16079","title":"Debiasing Masks: A New Framework for Shortcut Mitigation in NLU","created":"2022-10-28","cited_by_count":16},{"id":"2012.01604","title":"Going Beyond Classification Accuracy Metrics in Model Compression","created":"2020-12-03","cited_by_count":15},{"id":"2106.07849","title":"Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation","created":"2021-06-15","cited_by_count":15},{"id":"2208.00781","title":"Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods","created":"2022-07-26","cited_by_count":15},{"id":"2009.05423","title":"Achieving Adversarial Robustness via Sparsity","created":"2020-09-11","cited_by_count":14},{"id":"2201.01709","title":"The Effect of Model Compression on Fairness in Facial Expression Recognition","created":"2022-01-05","cited_by_count":13},{"id":"2110.10389","title":"Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias","created":"2021-10-20","cited_by_count":11},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11},{"id":"2304.12622","title":"Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures","created":"2023-04-25","cited_by_count":11},{"id":"2402.17729","title":"Towards Fairness-Aware Adversarial Learning","created":"2024-02-27","cited_by_count":11},{"id":"2405.08681","title":"Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis","created":"2024-05-14","cited_by_count":9},{"id":"2406.14686","title":"A Contrastive Learning Approach to Mitigate Bias in Speech Models","created":"2024-06-20","cited_by_count":9},{"id":"2111.13108","title":"Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment","created":"2021-11-25","cited_by_count":8},{"id":"2207.04546","title":"FairDistillation: Mitigating Stereotyping in Language Models","created":"2022-07-10","cited_by_count":8},{"id":"2210.05248","title":"Self-supervised debiasing using low rank regularization","created":"2022-10-11","cited_by_count":8},{"id":"2310.18590","title":"Using Early Readouts to Mediate Featural Bias in Distillation","created":"2023-10-28","cited_by_count":7},{"id":"2409.03303","title":"Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization","created":"2024-09-05","cited_by_count":6},{"id":"2305.03691","title":"Mining bias-target Alignment from Voronoi Cells","created":"2023-05-05","cited_by_count":5},{"id":"2312.10396","title":"How Far Can Fairness Constraints Help Recover From Biased Data?","created":"2023-12-16","cited_by_count":5},{"id":"2210.00891","title":"Information Removal at the bottleneck in Deep Neural Networks","created":"2022-09-30","cited_by_count":4},{"id":"2211.10285","title":"A Fair Loss Function for Network Pruning","created":"2022-11-18","cited_by_count":4},{"id":"2207.02000","title":"Disentangling private classes through regularization","created":"2022-07-05","cited_by_count":3},{"id":"2204.12941","title":"Unsupervised Learning of Unbiased Visual Representations","created":"2022-04-26","cited_by_count":2},{"id":"2407.17449","title":"Looking at Model Debiasing through the Lens of Anomaly Detection","created":"2024-07-24","cited_by_count":2},{"id":"2504.15991","title":"Efficient Adaptation of Deep Neural Networks for Semantic Segmentation in Space Applications","created":"2025-04-22","cited_by_count":1}],"next_cursor":null}