{"list":"other","total":90,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"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":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2003.10580","title":"Meta Pseudo Labels","created":"2020-03-23","cited_by_count":374},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"2104.07586","title":"See through Gradients: Image Batch Recovery via GradInversion","created":"2021-04-15","cited_by_count":326},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"2006.07709","title":"Auditing Differentially Private Machine Learning: How Private is Private SGD?","created":"2020-06-13","cited_by_count":218},{"id":"2101.04535","title":"Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning","created":"2021-01-11","cited_by_count":199},{"id":"2112.00059","title":"Evaluating Gradient Inversion Attacks and Defenses in Federated Learning","created":"2021-11-30","cited_by_count":196},{"id":"2003.00827","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","created":"2020-02-14","cited_by_count":153},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148},{"id":"2010.06121","title":"To be Robust or to be Fair: Towards Fairness in Adversarial Training","created":"2020-10-13","cited_by_count":137},{"id":"2007.14191","title":"Tempered Sigmoid Activations for Deep Learning with Differential Privacy","created":"2020-07-28","cited_by_count":122},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"1405.7085","title":"Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds","created":"2014-05-27","cited_by_count":107},{"id":"2110.14962","title":"Gradient Inversion with Generative Image Prior","created":"2021-10-28","cited_by_count":101},{"id":"2002.03206","title":"Characterizing Structural Regularities of Labeled Data in Overparameterized Models","created":"2020-02-08","cited_by_count":93},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87},{"id":"2012.03173","title":"Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification","created":"2020-12-06","cited_by_count":86},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86},{"id":"2011.03731","title":"On the Privacy Risks of Algorithmic Fairness","created":"2020-11-07","cited_by_count":82},{"id":"2110.15122","title":"CAFE: Catastrophic Data Leakage in Vertical Federated Learning","created":"2021-10-26","cited_by_count":76},{"id":"2009.06389","title":"Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy","created":"2020-09-10","cited_by_count":61},{"id":"2203.12609","title":"Improving the Fairness of Chest X-ray Classifiers","created":"2022-03-23","cited_by_count":52},{"id":"2207.04380","title":"Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions","created":"2022-07-10","cited_by_count":52},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52},{"id":"1412.8659","title":"Deep Roto-Translation Scattering for Object Classification","created":"2014-12-30","cited_by_count":50},{"id":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48},{"id":"2002.11651","title":"Fair Learning with Private Demographic Data","created":"2020-02-26","cited_by_count":46},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46},{"id":"2010.13365","title":"Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy","created":"2020-10-26","cited_by_count":45},{"id":"1910.13427","title":"Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications","created":"2019-10-29","cited_by_count":43},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41},{"id":"2202.12219","title":"Debugging Differential Privacy: A Case Study for Privacy Auditing","created":"2022-02-24","cited_by_count":40},{"id":"1901.09335","title":"Augment your batch: better training with larger batches","created":"2019-01-27","cited_by_count":37},{"id":"2010.06667","title":"Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings","created":"2020-10-13","cited_by_count":37},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37},{"id":"1906.00389","title":"Disparate Vulnerability to Membership Inference Attacks","created":"2019-06-02","cited_by_count":35},{"id":"2105.13343","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","created":"2021-05-27","cited_by_count":33},{"id":"2106.12576","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?","created":"2021-06-22","cited_by_count":33},{"id":"2203.00324","title":"Differentially private training of residual networks with scale normalisation","created":"2022-03-01","cited_by_count":26},{"id":"2007.05089","title":"The Trade-Offs of Private Prediction","created":"2020-07-09","cited_by_count":22},{"id":"2110.06255","title":"Not all noise is accounted equally: How differentially private learning benefits from large sampling rates","created":"2021-10-12","cited_by_count":21},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19},{"id":"2306.06076","title":"Differentially Private Image Classification by Learning Priors from Random Processes","created":"2023-06-08","cited_by_count":19},{"id":"2206.03985","title":"How unfair is private learning ?","created":"2022-06-08","cited_by_count":18},{"id":"2210.13662","title":"Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano","created":"2022-10-24","cited_by_count":17},{"id":"2302.01622","title":"Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging","created":"2023-02-03","cited_by_count":17},{"id":"2306.08842","title":"ViP: A Differentially Private Foundation Model for Computer Vision","created":"2023-06-15","cited_by_count":17},{"id":"2210.02156","title":"Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search","created":"2022-10-05","cited_by_count":15},{"id":"2003.03699","title":"Removing Disparate Impact of Differentially Private Stochastic Gradient Descent on Model Accuracy","created":"2020-03-08","cited_by_count":13},{"id":"2106.05915","title":"Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays","created":"2021-06-10","cited_by_count":11},{"id":"2305.18159","title":"The Misuse of AUC: What High Impact Risk Assessment Gets Wrong","created":"2023-05-29","cited_by_count":10},{"id":"2306.03962","title":"PILLAR: How to make semi-private learning more effective","created":"2023-06-06","cited_by_count":10},{"id":"1806.11311","title":"Guaranteed Deterministic Bounds on the Total Variation Distance between Univariate Mixtures","created":"2018-06-29","cited_by_count":7},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7},{"id":"2005.09209","title":"Fair Inputs and Fair Outputs: The Incompatibility of Fairness in Privacy and Accuracy","created":"2020-05-19","cited_by_count":6},{"id":"2306.06503","title":"Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy","created":"2023-06-10","cited_by_count":6},{"id":"2301.13104","title":"Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models","created":"2023-01-30","cited_by_count":4}],"next_cursor":null}