We have accepted 36 papers with a 55% acceptance rate. Among the accepted papers, the following 6 outstanding papers (9% acceptance rate) were further selected to have contributed talks (a 12-min presentation + 3-min live Q/A). Congratulations!

• A Unified Framework to Understand Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective
  Xinwei Zhang (University of Minnesota), Mingyi Hong (University of Minnesota), Nicola Elia (University of Minnesota)
• Architecture Personalization in Resource-constrained Federated Learning
  Mi Luo (National University of Singapore), Fei Chen (Huawei Noah's Ark Lab), Zhenguo Li (Huawei Noah's Ark Lab), Jiashi Feng ()
• Efficient and Private Federated Learning with Partially Trainable Networks
  Hakim Sidahmed (Google Research), Zheng Xu (Google Research), Ankush Garg (Google), Yuan Cao (Google Brain), Mingqing Chen (Google)
• FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning
  Yi Zhou (IBM Almaden Research Center), Parikshit Ram (IBM Research AI), Theodoros Salonidis (IBM T.J. Watson Research Center), Nathalie Baracaldo ("IBM Almaden Research Center, USA"), Horst Samulowitz (IBM Research), Heiko Ludwig (IBM Research)
• Personalized Neural Architecture Search for Federated Learning
  Minh Hoang (Carnegie Mellon University), Carl Kingsford (Carnegie Mellon University)
• Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective
  Margalit R Glasgow (Stanford University), Honglin Yuan (Stanford), Tengyu Ma (Stanford)

Below is the full list of accepted papers. Each accepted paper will be presented as poster. Congratulations again to all the authors of accepted papers!

• A Unified Framework to Understand Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective [Paper] [Supplemental]
  Xinwei Zhang (University of Minnesota), Mingyi Hong (University of Minnesota), Nicola Elia (University of Minnesota)
• Advanced Free-rider Attacks in Federated Learning [Paper] [Supplemental]
  Zhenqian Zhu (Harbin Institute of Technology，Shenzhen), Jiangang Shu (Pengcheng Laboratory), Zou Xing (Peng Cheng Laboratory), Xiaohua Jia (City University of Hong Kong)
• Architecture Personalization in Resource-constrained Federated Learning [Paper] [Supplemental]
  Mi Luo (National University of Singapore), Fei Chen (Huawei Noah's Ark Lab), Zhenguo Li (Huawei Noah's Ark Lab), Jiashi Feng ()
• Bayesian Framework for Gradient Leakage [Paper] [Supplemental]
  Mislav Balunovic (ETH Zurich), Dimitar I Dimitrov (ETH Zürich), Robin Staab (ETH Zurich), Martin Vechev (ETH Zurich)
• Bayesian SignSGD Optimizer for Federated Learning [Paper] [Supplemental]
  Paulo Ferreira (Dell Technologies), Pablo Silva (Dell Technologies), Vinicius M Gottin (Dell Technologies), Roberto Stelling (Dell Technologies), Tiago Calmon (Dell Technologies)
• Certified Federated Adversarial Training [Paper] [Supplemental]
  Giulio Zizzo (IBM Research), Ambrish Rawat (IBM Research), Mathieu Sinn (IBM Research), Sergio Maffeis (Imperial College London), Chris Hankin (Imperial College London)
• Certified Robustness for Free in Differentially Private Federated Learning [Paper] [Supplemental]
  Chulin Xie (University of Illinois at Urbana-Champaign), Yunhui Long (University of Illinois), Pin-Yu Chen (IBM Research), Krishnaram Kenthapadi (Amazon), Bo Li (UIUC)
• Contribution Evaluation in Federated Learning: Examining Current Approaches [Paper] [Supplemental]
  Jonathan Passerat-Palmbach (Imperial College London / ConsenSys Health), Vasilis Siomos (Imperial College London)
• CosSGD: Communication-Efficient Federated Learning with a Simple Cosine-Based Quantization [Paper]
  Yang He (CISPA Helmholtz Center for Information Security), Hui-Po Wang (CISPA Helmholtz Center for Information Security), Maximilian Zenk (), Mario Fritz (CISPA Helmholtz Center for Information Security)
• Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer [Paper] [Supplemental]
  Hongyan Chang (National University of Singapore), Virat Shejwalkar (UMass Amherst), Reza Shokri (NUS), Amir Houmansadr (University of Massachusetts Amherst)
• Decentralized Personalized Federated Min-Max Problems [Paper] [Supplemental]
  Ekaterina Borodich (MIPT), Aleksandr Beznosikov (Moscow Institute of Physics and Technology (National Research University)), Abdurakhmon Sadiev (Moscow Institute of Physics and Technology), Vadim Sushko (Bosch Center for Artificial Intelligence), Alexander Gasnikov (Moscow Institute of Physics and Technology)
• Detecting Poisoning Nodes in Federated Learning by Ranking Gradients [Paper] [Supplemental]
  Wanchuang Zhu (The University of Sydney), Benjamin ZH Zhao (Macquarie University), Simon Luo (The University of Sydney), Ke Deng (Tsinghua University)
• Efficient and Private Federated Learning with Partially Trainable Networks [Paper] [Supplemental]
  Hakim Sidahmed (Google Research), Zheng Xu (Google Research), Ankush Garg (Google), Yuan Cao (Google Brain), Mingqing Chen (Google)
• FairFed: Enabling Group Fairness in Federated Learning [Paper] [Supplemental]
  Yahya H. Ezzeldin (University of Southern California ), Shen Yan (University of Southern California), Chaoyang He (University of Southern California), Emilio Ferrara (University of Southern California, USA), Salman Avestimehr (University of Southern California)
• FedBABU: Towards Enhanced Representation for Federated Image Classification [Paper] [Supplemental]
  Jaehoon Oh (KAIST), SangMook Kim (KAIST), Se-Young Yun (KAIST)
• Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning [Paper] [Supplemental]
  Sean M Hendryx (University of Arizona), Dharma Raj KC (University of Arizona), Bradley L Walls (Arete), Clayton Morrison (University of Arizona)
• Federating for Learning Group Fair Models [Paper] [Supplemental]
  Afroditi Papadaki (University College London), Natalia L Martinez (Duke University), Martin Bertran (Duke University), Guillermo Sapiro (Duke University), Miguel Rodrigues (University College London)
• Gradient Masking for Generalization in Heterogenous Federated Learning [Paper] [Supplemental]
  Irene Tenison (Mila/UdeM), Sai Aravind Sreeramadas (MILA), Vaikkunth Mugunthan (MIT), Eugene Belilovsky (MILA), Irina Rish (Mila/UdeM)
• FedJAX: Federated learning simulation with JAX [Paper]
  Jae Ro (Google Research), Ananda Theertha Suresh (Google), Ke Wu (Google)
• FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning [Paper] [Supplemental]
  Elnur Gasanov (KAUST), Ahmed Khaled (KAUST), Samuel Horváth (KAUST), Peter Richtarik (KAUST)
• FedRAD: Federated Robust Adaptive Distillation [Paper] [Supplemental]
  Stefán P Sturluson (Imperial College London), Samuel Trew (Imperial College London), Luis Muñoz-González (Imperial College London), Matei George Nicolae Grama (Imperial College London), Jonathan Passerat-Palmbach (Imperial College London / ConsenSys Health), Daniel Rueckert (Imperial College London), Amir Alansary (Imperial College London)
• FeO2: Federated Learning with Opt-Out Differential Privacy [Paper]
  Nasser Aldaghri (University of Michigan), Hessam Mahdavifar (University of Michigan), Ahmad Beirami (Facebook AI)
• FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning [Paper] [Supplemental]
  Yi Zhou (IBM Almaden Research Center), Parikshit Ram (IBM Research AI), Theodoros Salonidis (IBM T.J. Watson Research Center), Nathalie Baracaldo ("IBM Almaden Research Center, USA"), Horst Samulowitz (IBM Research), Heiko Ludwig (IBM Research)
• Iterated Vector Fields and Conservatism, with Applications to Federated Learning [Paper] [Supplemental]
  Zachary Charles (Google Research), Keith Rush (Google Research)
• Learning Federated Representations and Recommendations with Limited Negatives [Paper] [Supplemental]
  Lin Ning (Google Research), Karan Singhal (Google Research), Ellie X. Zhou (Google), Sushant Prakash (Google Research)
• Minimal Model Structure Analysis for Input Reconstruction in Federated Learning [Paper]
  Jia Qian (Technical University of Denmark), Hiba Nassar ( Technical University of Denmark ), Lars Kai Hansen (Technical University of Denmark)
• Personalized Neural Architecture Search for Federated Learning [Paper] [Supplemental]
  Minh Hoang (Carnegie Mellon University), Carl Kingsford (Carnegie Mellon University)
• Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses [Paper] [Supplemental]
  Andrew Lowy (USC), Meisam Razaviyayn (USC)
• Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach [Paper] [Supplemental]
  Xiaoyang Wang (University of Illinois at Urbana-Champaign), Han Zhao (University of Illinois at Urbana-Champaign), Klara Nahrstedt (University of Illinois at Urbana-Champaign), Sanmi Koyejo (Illinois/Google)
• RVFR: Robust Vertical Federated Learning via Feature Subspace Recovery [Paper] [Supplemental]
  Jing Liu (UIUC), Chulin Xie (University of Illinois at Urbana-Champaign), Krishnaram Kenthapadi (Amazon), Sanmi Koyejo (Illinois/Google), Bo Li (UIUC)
• Scalable Average Consensus with Compressed Communications [Paper] [Supplemental]
  Mohammad Taha Toghani (Rice University), Cesar Uribe (Rice University)
• Secure Aggregation for Buffered Asynchronous Federated Learning [Paper] [Supplemental]
  Jinhyun So (University of Southern California), Ramy E. Ali (University of Southern California), Basak Guler (University of California, Riverside), Salman Avestimehr (University of Southern California)
• Secure Byzantine-Robust Distributed Learning via Clustering [Paper] [Supplemental]
  Raj Kiriti Velicheti (UIUC), Derek Xia (UIUC), Sanmi Koyejo (Illinois/Google)
• Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective [Paper] [Supplemental]
  Margalit R Glasgow (Stanford University), Honglin Yuan (Stanford), Tengyu Ma (Stanford)
• WAFFLE: Weighted Averaging for Personalized Federated Learning [Paper] [Supplemental]
  Martin Beaussart (EPFL), Mary-Anne Hartley (EPFL), Felix Grimberg (EPFL), Martin Jaggi (EPFL)
• What Do We Mean by Generalization in Federated Learning? [Paper] [Supplemental]
  Honglin Yuan (Stanford), Warren R Morningstar (Google Research), Lin Ning (Google Research), Karan Singhal (Google Research)