Accepted Papers

Accepted Papers

  • MetaDataset: A Dataset of Datasets for Evaluating Distribution Shifts and Training Conflicts, Weixin Liang (Stanford University)*; James Zou (Stanford University)

  • Towards Principled Disentanglement for Domain Generalization, Hanlin Zhang (Carnegie Mellon University)*; Yi-Fan Zhang (NLPR, China); Weiyang Liu (University of Cambridge); Adrian Weller (University of Cambridge); Bernhard Schölkopf (MPI for Intelligent Systems, Tübingen); Eric Xing (MBZUAI, CMU, and Petuum Inc.)

  • An Efficient DP-SGD Mechanism for Large Scale NLP Models, Christophe Dupuy (Amazon)*; Radhika Arava (Amazon); Rahul Gupta (Amazon); Anna Rumshisky (University of Massachusetts Lowell)

  • CDCGen: Cross-Domain Conditional Generation via Normalizing Flows and Adversarial Training, Hari Prasanna Das (UC Berkeley)*; Ryan Tran (UC Berkeley); Japjot Singh (UC Berkeley); Yu Wen Lin (UC Berkeley); Costas J. Spanos (University of California at Berkeley)

  • Measuring Fairness in Generative Models, Christopher TH Teo (Singapore University of Technology and Design)*; Ngai-Man Cheung (Singapore University of Technology and Design)

  • BRR: Preserving Privacy of Text Data Efficiently on Device, Ricardo Silva Carvalho (Simon Fraser University); Theodore Vasiloudis (Amazon.com)*; Oluwaseyi Feyisetan (Amazon Research)

  • AutoMixup: Learning mix-up policies with Reinforcement Learning, Long Minh Luu (International University - VNUHCM)*; Zeyi Huang (Carnegie Mellon University); Haohan Wang (Carnegie Mellon University)

  • Deep Causal Inequalities: Demand Estimation in Differentiated Products Markets, Edvard Bakhitov (University of Pennsylvania); Amandeep Singh (The Wharton School)*; Jiding Zhang (The Wharton School)

  • Regularization and False Alarms Quantification: Towards an Approach to Assess the Economic Value of Machine Learning, Nima Safaei (Scotiabank)*; Pooria Assadi (California State University Sacramento)

  • Model Mis-specification and Algorithmic Bias, Runshan Fu (Carnegie Mellon University); Yangfan Liang (Carnegie Mellon University)*; Peter Zhang

  • Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods, Terrance Liu (Carnegie Mellon University)*; Giuseppe Vietri (University of Minnesota); Steven Wu (Carnegie Mellon University)

  • Adversarial Stacked Auto-Encoders for Fair Representation Learning, Patrik Joslin Kenfack (Innopolis University)*; Adil Khan (Innopolis University); Rasheed Hussain (Innopolis University); S.M. Ahsan Kazmi (Innopolis University)

  • An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises, Mayana Wanderley Pereira (Microsoft)*; Meghana Kshirsagar (Microsoft); Sumit Mukherjee (Microsoft); Rahul Dodhia (Microsoft); Juan M Lavista Ferres (Microsoft)

  • Deep AutoAugment, Yu Zheng (Michigan State University); Zhi Zhang (Amazon); Shen Yan (Michigan State University); Mi Zhang (Michigan State University)*

  • Social Norm Bias: Residual Harms of "Fair" Algorithms, Myra Cheng (California Institute of Technology)*; Maria De-Arteaga (University of Texas at Austin); Lester Mackey (Microsoft Research); Adam Tauman Kalai (Microsoft Research)

  • A Standardized Data Collection Toolkit for Model Benchmarking, Avanika Narayan (Stanford University)*; Piero Molino (Uber AI); Willie Neiswanger (Stanford University); Karan Goel (Stanford); Christopher Re (Stanford University)

  • Bayesian Regression from Multiple Sources of Weak Supervision, Putra Manggala (University of Amsterdam)*; Holger Hoos (Leiden Institute of Advanced Computer Science, Leiden University); Eric Nalisnick (University of Amsterdam)

  • Data Considerations in Graph Representation Learning for Supply Chain Networks, Ajmal Aziz (University of Cambridge); Edward Elson Kosasih (University of Cambridge)*; Ryan-Rhys Griffiths (University of Cambridge); Alexandra Brintrup (University of Cambridge)

  • DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?, Archit Uniyal (Openmined); Rakshit Naidu (Carnegie Mellon University)*; Sasikanth Kotti (OpenMined; IIT Jodhpur); Patrik Joslin Kenfack (Innopolis University); Sahib Singh (Ford Research (R&A), OpenMined); Fatemeh Mireshghallah (University of California, San Diego)

  • Benchmarking Differential Privacy and Federated Learning for BERT Models, Priyam Basu (Manipal Institute of Technology); Tiasa Singha Roy (Manipal Institute of Technology); Rakshit Naidu (Carnegie Mellon University)*; Zumrut Muftuoglu (Yildiz Technical University); Sahib Singh (OpenMined; Ford R&A); Fatemeh Mireshghallah (University of California, San Diego)