International Workshop on Trustable, Verifiable and Auditable Federated Learning in Conjunction with AAAI 2022 (FL-AAAI-22)


Submission Due: November 12, 2021 November 30, 2021 (23:59:59 AoE)
Notification Due: December 03, 2021 January 05, 2022 (23:59:59 AoE)
Final Version Due: February 15, 2022 (23:59:59 AoE)
Workshop Date: March 01, 2022
Venue: Virtual

Invited Talks

   

Title: Reliable Federated Learning for Mobile Networks

Speaker: Dusit Niyato, Nanyang Technological University (NTU), Singapore

Biography
Dusit Niyato is currently a professor in the School of Computer Science and Engineering, at Nanyang Technological University, Singapore. He is a Fellow of the IEEE. He received B.Eng. from King Mongkuts Institute of Technology Ladkrabang (KMITL), Thailand in 1999 and Ph.D. in Electrical and Computer Engineering from the University of Manitoba, Canada in 2008. His research interests are in the areas of Internet of Things (IoT), machine learning, and incentive mechanism design.

   

Title: Federated Learning Systems: A New Holy Grail for System Research in Data Privacy and Protection?

Speaker: Bingsheng He, National University of Singapore (NUS), Singapore

Biography
Dr. Bingsheng He is currently a Dean's Chair Associate Professor and Vice-Dean (Research) at School of Computing, National University of Singapore. Before that, he was a faculty member in Nanyang Technological University, Singapore (2010-2016), and held a research position in the System Research group of Microsoft Research Asia (2008-2010), where his major research was building high performance cloud computing systems for Microsoft. He got the Bachelor degree in Shanghai Jiao Tong University (1999-2003), and the Ph.D. degree in Hong Kong University of Science & Technology (2003-2008). His current research interests include cloud computing, database systems and high performance computing. His papers are published in prestigious international journals (such as ACM TODS and IEEE TKDE/TPDS/TC) and proceedings (such as ACM SIGMOD, VLDB/PVLDB, ACM/IEEE SuperComputing, ACM HPDC, and ACM SoCC). He has been awarded with the IBM Ph.D. fellowship (2008), NVIDIA Academic Partnership (2011), Adaptive Compute Research Cluster from Xilinx (2020) and ACM distinguished member (class 2020). Since 2010, he has (co-)chaired a number of international conferences and workshops, including IEEE CloudCom 2014/2015, BigData Congress 2018 and ICDCS 2020. He has served in editor board of international journals, including IEEE Transactions on Cloud Computing (IEEE TCC), IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS), IEEE Transactions on Knowledge and Data Engineering (TKDE), Springer Journal of Distributed and Parallel Databases (DAPD) and ACM Computing Surveys (CSUR). He is an ACM Distinguished member (class of 2020).

   

Title: Challenges in Privately Distributing Training Data

Speaker: Nicholas Carlini, Google Brain, USA

Biography
Nicholas Carlini is a research scientist at Google Brain. He studies the security and privacy of machine learning, for which he has received best paper awards at ICML, USENIX Security and IEEE S&P. He obtained his PhD from the University of California, Berkeley in 2018.

   

Title: Towards Building a Private, Robust and Fair Federated Learning System

Speaker: Lingjuan Lyu, Sony AI, Japan

Biography
Lingjuan Lyu is a Senior Research Scientist and Team Leader at Sony AI. Her current research interests span distributed/federated learning, privacy, robustness, fairness, and edge intelligence. Her work was supported by an IBM Ph.D. Fellowship, ANU Translational Fellowship, etc. She obtained her PhD from the University of Melbourne. Her work has received best paper awards from the top conferences.

   

Title: TBD

Speaker: Dacheng Tao, JD.com, China

Biography
Dacheng Tao received his BEng from the University of Science and Technology of China (USTC), his MPhil from the Chinese University of Hong Kong, and his PhD from the University of London. He is currently the director of the JD Explore Academy and a vice president in JD.com, an advisor and chief scientist of the digital science institute in the University of Sydney (USYD), distinguished visiting professor in Tsinghua University, and grand master adjunct professor in USTC. Previously, he was a Professor and ARC Laureate Fellow in USYD, Professor and ARC Future Fellow in the University of Technology Sydney, a Nanyang Assistant Professor in the Nanyang Technological University, an Assistant Professor in the Hong Kong Polytechnic University. His research interests spread across subareas in artificial intelligence (AI), including computer vision, data mining, deep learning, image processing, and machine learning. His research results have expounded in 400+ publications at prestigious journals and conferences, with several best paper awards, such as the IEEE ICDM'07 best theory/algorithm paper runner up award, the IEEE ICDM'13 best student paper award, the 2014 ICDM 10-year highest-impact paper award, the IJCAI 2017 distinguished student paper award, the IJCAI 2018 distinguished paper award, and the 2017 IEEE signal processing society best paper award. He has been ranked as a Highly-Cited Researcher in Engineering since 2014 and Computer Science since 2015. His publications have been cited 66K+ times, and his H-Index is 132. He received the 2015 Australian Museum Scopus-Eureka Prize, the 2015 ACS Gold Disruptor Award, the 2015 UTS Vice-Chancellor's Medal for Exceptional Research, the 2018 IEEE ICDM Research Contributions Award, the 2020 USYD Vice-Chancellor's Award for Outstanding Research, and the 2020 Australian Museum Eureka Prize for Excellence in Data Science. He is a Fellow of the IEEE, OSA, IAPR, AAAS, ACM, and the Australian Academy of Science.


Accepted Papers (Oral Presentation)

  1. Chen Chen, Jie Zhang and Lingjuan Lyu. GEAR: A Margin-based Federated Adversarial Training Approach
  2. Chengyi Yang, Jia Liu, Hao Sun, Tongzhi Li and Zengxiang Li. WT-Shapley: Efficient and Effective Incentive Mechanism in Federated Learning for Intelligent Safety Inspection
  3. Chaoyang He, Zhengyu Yang, Erum Mushtaq, Sunwoo Lee, Mahdi Soltanolkotabi and Salman Avestimehr. SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision
  4. Sunwoo Lee, Anit Sahu, Chaoyang He and Salman Avestimehr. Partial Model Averaging in Federated Learning: Performance Guarantees and Benefits
  5. Chaoyang He, Alay Dilipbhai Shah, Zhenheng Tang, Di Fan, Adarshan Naiynar Sivashunmugam, Keerti Bhogaraju, Mita Shimpi, Li Shen, Xiaowen Chu, Mahdi Soltanolkotabi and Salman Avestimehr. FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
  6. Chen Chen, Lingjuan Lyu, Yuchen Liu, Fangzhao Wu, Chaochao Chen and Gang Chen. Byzantine-resilient Federated Learning via Gradient Memorization
  7. Jiahui Geng, Yongli Mou, Feifei Li, Qing Li, Oya Beyan, Stefan Decker and Chunming Rong. Towards General Deep Leakage in Federated Learning
  8. Shraman Pal, Mansi Uniyal, Jihong Park, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Moongu Jeon and Jinho Choi. Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning
  9. Jiyue Huang, Chi Hong, Yang Liu, Lydia Y. Chen and Stefanie Roos. Tackling Mavericks in Federated Learning via Adaptive Client Selection Strategy
  10. Yuezhou Wu, Yan Kang, Jiahuan Luo, Yuanqin He and Qiang Yang. FedCG: Leverage Conditional GAN for Protecting Privacy and MaintainingCompetitive Performance in Federated Learning
  11. Hangrui Cao, Qiying Pan, Yifei Zhu and Jiangchuan Liu. Birds of a Feather Help: Context-aware Client Selection for Federated Learning
  12. Yuchen Zeng, Hongxu Chen and Kangwook Lee. Improving Fairness via Federated Learning
  13. Yuting He, Yiqiang Chen, Xiaodong Yang, Yingwei Zhang and Bixiao Zeng. Class-Wise Adaptive Self Distillation for Heterogeneous Federated Learning
  14. Jichan Chung, Kangwook Lee and Kannan Ramchandran. Federated Unsupervised Clustering with Generative Models
  15. Haizhou Shi, Youcai Zhang, Zijin Shen, Siliang Tang, Yaqian Li, Yandong Guo and Yueting Zhuang. Towards Communication-Efficient and Privacy-Preserving Federated Representation Learning
  16. Hamid Mozaffari, Virat Shejwalkar and Amir Houmansadr. Robust Federated Learning By Training on Parameter Ranks
  17. Yujia Wang, Lu Lin and Jinghui Chen. Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
  18. Tahseen Rabbani, Brandon Feng, Yifan Yang, Arjun Rajkumar, Amitabh Varshney and Furong Huang. Comfetch: Federated Learning of Large Networks on Memory-Constrained Clients via Sketching

Accepted Papers (Poster Presentation)

  1. Jingoo Han, Ahmad Faraz Khan, Syed Zawad, Ali Anwar, Nathalie Baracaldo Angel, Yi Zhou, Feng Yan and Ali R. Butt. Tokenized Incentive for Federated Learning
  2. Morris Stallmann and Anna Wilbik. Towards Federated Clustering: A Federated Fuzzy c-Means Algorithm (FFCM)
  3. Chao Jin, Jun Wang, Sin Gee Teo, Le Zhang, Cs Chan, Qibin Hou and Khin Mi Mi Aung. End-to-End Secure and Efficient Federated Learning for XGBoost
  4. K. R. Jayaram, Vinod Muthusamy, Gegi Thomas, Ashish Verma and Mark Purcell. Lambda FL : Serverless Aggregation For Federated Learning
  5. Jinhyun So, Ramy E. Ali, Basak Guler, Jiantao Jiao and Salman Avestimehr. Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning
  6. Ninareh Mehrabi, Cyprien de Lichy, John McKay, Cynthia He and William Campbell. Towards Multi-Objective Statistically Fair Federated Learning
  7. Ashish Gupta, Tony Luo, Mao Ngo and Sajal Das. MUD-HoG: Malicious and Unreliable Clients Detection using History of Gradients in Federated Learning
  8. Erum Mushtaq, Chaoyang He, Jie Ding and Salman Avestimehr. SPIDER: Searching Personalized Neural Architecture for Federated Learning
  9. Afra Mashhadi, Alex Kyllo and Reza Parizi. Fairness in Federated Learning for Spatial-Temporal Applications
  10. Meijie Wen and Shaofu Yang. Decentralized Stochastic Optimization with Fixed-Time Computation and Compressed Communication
  11. Wenqing Zhang, Yang Qiu, Song Bai, Rui Zhang, Xiaolin Wei and Xiang Bai. FedOCR: Efficient and Secure Federated Learning for Scene Text Recognition
  12. Charles Lu and Jayashree Kalpathy-Cramer. Distribution-Free Federated Learning with Conformal Predictions
  13. Lianlian Jiang, Yuexuan Wang, Wenyi Zheng, Chao Jin, Zengxiang Li and Sin G. Teo. LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Data
  14. Haoran Shi, Yali Jiang, Han Yu, Yonghui Xu and Lizhen Cui. MVFLS: Multi-participant Vertical Federated Learning based on Secret Sharing
  15. Zexi Yao, Chao Jin, Mohamed Ragab, Khin Mi Mi Aung and Xiaoli Li. DiagNet: Machine Fault Diagnosis Using Federated Transfer Learning in Low Data Regimes
  16. Khouloud Abdelli, Joo Yeon Cho and Stephan Pachnicke. Secure and Robust Federated Learning for Predictive Maintenance in Optical Networks
  17. Balázs Pejó and Gergely Biczok. Quality Inference in Federated Learning with Secure Aggregation [Poster]
  18. Riadh Ben Chaabene, Darine Ameyed and Mohamed Cheriet. Leveraging Centric Data Federated Learning Using Blockchain For Integrity Assurance
  19. Hyunsu Mun and Youngseok Lee. FLHub: a Federated Learning model sharing service
  20. Sheng Guo, Zengxiang Li, Hui Liu, Shubao Zhao and Cheng Hao Jin. Personalized Federated Learning for Multi-task Fault Diagnosis of Rotating Machinery

Call for Papers

Federated learning (FL) is one promising machine learning approach that trains a collective machine learning model using sharing data owned by various parties. It leverages many emerging privacy-reserving technologies (SMC, Homomorphic Encryption, differential privacy, etc.) to protect data owner privacy in FL. It has been gained popularity in some domains such as image classification, speech recognition, smart city, and healthcare. However, FL also faces multiple challenges that may potentially limit its applications in real-world use scenarios. For example, FL is still at the risk of various kinds of attacks that may result in leakage of individual data source privacy or degraded joint model accuracy. In other words, many existing FL solutions are still exposed to various security and privacy threats. This workshop aims to bring together FL researchers and practitioners to address the additional security and privacy threats and challenges in FL To make its mass adoption and widespread acceptance in the community. For example, privacy-specific threats in FL, training/inference phase attacks; data poisoning, model poisoning, how to handle Non-IID data without affecting the model performance, lacking trust from the FL participant, how to gain confidence by interpreting FL model, scheme of contributions and rewards to FL participants for improving an FL model, social and corporate responsibility towards the adoption of FL, imbalance data among FL participants, methods to verify and proof the correctness of FL computation, etc. The discussion in the workshop can lead implementing FL solutions that are more accurate, robust and interpretable, gain the trust of the FL participants.

Topics of interest include, but are not limited to:
  • Interpretable Federated Learning
  • Trade-Off between Privacy-Preserving and Explainable Federated Learning
  • Federated Learning Multi-Party Computation
  • Federated Learning Homomorphic Encryption
  • Federated Learning Differential Privacy
  • Federated Transfer Learning
  • Federated Learning Personalization Techniques
  • Federated Learning Attacks and Defenses
  • Federated Learning Blockchain Network
  • Federated Learning Secure Aggregation
  • Federated Learning Fairness and Accuracy
  • Federated Learning with Non-IID Data
  • Federated Learning Incentive Mechanism
  • Federated Learning Meets Mean-Field Game Theory
  • Federated Learning-based Corporate Social Responsibility
  • Social Responsible Federated Learning
  • Decentralized Federated Learning
  • Vertical Federated Learning

More information on previous workshops can be found here.


Submission Instructions

Each submission can be up to 9 pages including references. The submitted papers must be written in English and in PDF format according to the AAAI-22 template. All submitted papers will be under a single-blinded peer review for their novelty, technical quality, impact, reproducibility, and so on. Submission will be accepted via the Easychair submission website.

Easychair submission site: https://easychair.org/conferences/?conf=fl-aaai-22

For enquiries, please email to: fl-aaai-22@easychair.org


Publications

Accepted papers will be invited to submit to a special issue of IEEE Transactions on Big Data.


Organizing Committee


Program Committee

  • Ali Anwar (IBM)
  • Alysa Ziying Tan (Alibaba-NTU Singapore Joint Research Institute)
  • Anran Li (University of Science and Technology of China)
  • Bing Luo (City University of Hong Kong, Shenzhen)
  • Bingsheng He (National University of Singapore)
  • Boi Faltings (École Polytechnique Fédérale de Lausanne)
  • Chaoyang He (University of Southern California)
  • Chuizheng Meng (University of Southern California)
  • Di Chai (The Hong Kong University of Science and Technology)
  • Dianbo Liu (Massachusetts Institute of Technology)
  • Dimitrios Papadopoulos (The Hong Kong University of Science and Technology)
  • Farzin Haddadpour (Yale University)
  • Feng Yan (University of Nevada, Reno)
  • Graham Cormode (The University of Warwick)
  • Grigory Malinovsky (King Abdullah University of Science and Technology)
  • Hongyi Wang (University of Wisconsin - Madison)
  • Hongyuan Zhan (Facebook AI)
  • Jiankai Sun (The Ohio State University)
  • Jianshu Weng (AI Singapore)
  • Jianyu Wang (Carnegie Mellon University)
  • Jihong Park (Deakin University)
  • Jinhyun So (University of Southern California)
  • Jun Zhao (Nanyang Technological University)
  • Junxue Zhang (The Hong Kong University of Science and Technology)
  • Kallista Bonawitz (Google)
  • Kevin Hsieh (Microsoft Research)
  • Lei Jiao (University of Oregon)
  • Lifeng Sun (Tsinghua University)
  • Lingjuan Lyu (Sony AI)
  • Mehrdad Mahdavi (The Pennsylvania State University)
  • Mingyue Ji (University of Utah)
  • Mingzhe Chen (Princeton University)
  • Peng Zhang (Guangzhou University)
  • Pengwei Xing (Nanyang Technological University)
  • Praneeth Vepakomma (Massachusetts Institute of Technology)
  • Rui Liu (Nanyang Technological University)
  • Rui-Xiao Zhang (Tsinghua University)
  • Samuel Horvath (King Abdullah University of Science and Technology)
  • Sebastian Urban Stich (École Polytechnique Fédérale de Lausanne)
  • Shangwei Guo (Chongqing University)
  • Shiqiang Wang (IBM)
  • Siwei Feng (Soochow University)
  • Songze Li (The Hong Kong University of Science and Technology)
  • Theodoros Salonidis (IBM)
  • Tian Li (Carnegie Mellon University)
  • Wei Yang Bryan Lim (Nanyang Technological university)
  • Xiaohu Wu (Nanyang Technological University)
  • Xiaoli Tang (Nanyang Technological University)
  • Xu Guo (Nanyang Technological University)
  • Yi Zhou (IBM Almaden Research Center)
  • Yiyang Pei (Singapore Institute of Technology)
  • Yuan Liu (Northeastern University)
  • Yuang Jiang (Yale University)
  • Yuxin Shi (Nanyang Technological University)
  • Zehui Xiong (Singapore University of Technology and Design)
  • Zelei Liu (Nanyang Technological University)
  • Zheng Xu (Google)
  • Zhuan Shi (University of Science and Technology of China)
  • Zichen Chen (University of California, Santa Barbara)

Sponsored by

  Sony AI was founded on April 1, 2020, with the mission to "unleash human imagination and creativity with AI." To achieve this, Sony AI is currently pursuing four flagship projects aimed at the evolution and application of AI technology in the areas of Gaming, Imaging & Sensing, Gastronomy, and AI Ethics. In addition to driving its own cutting edge R&D activities, Sony AI partners with Sony Group companies to leverage Sony’s unique assets and capabilities in the realm of imaging and sensing, robotics, and entertainment, and proactively seeks for external partnership opportunities. For more information, please visit https://ai.sony.

Organized by