Skip to yearly menu bar Skip to main content

Workshop

Federated Learning: Recent Advances and New Challenges

Shiqiang Wang ⋅ Nathalie Baracaldo ⋅ Olivia Choudhury ⋅ Gauri Joshi ⋅ Peter Richtarik ⋅ Praneeth Vepakomma ⋅ Han Yu

Project Page [ Contact: fl-neurips-2022@googlegroups.com ]

Abstract

Training machine learning models in a centralized fashion often faces significant challenges due to regulatory and privacy concerns in real-world use cases. These include distributed training data, computational resources to create and maintain a central data repository, and regulatory guidelines (GDPR, HIPAA) that restrict sharing sensitive data. Federated learning (FL) is a new paradigm in machine learning that can mitigate these challenges by training a global model using distributed data, without the need for data sharing. The extensive application of machine learning to analyze and draw insight from real-world, distributed, and sensitive data necessitates familiarization with and adoption of this relevant and timely topic among the scientific community.

Despite the advantages of FL, and its successful application in certain industry-based cases, this field is still in its infancy due to new challenges that are imposed by limited visibility of the training data, potential lack of trust among participants training a single model, potential privacy inferences, and in some cases, limited or unreliable connectivity.

The goal of this workshop is to bring together researchers and practitioners interested in FL. This day-long event will facilitate interaction among students, scholars, and industry professionals from around the world to understand the topic, identify technical challenges, and discuss potential solutions. This will lead to an overall advancement of FL and its impact in the community, while noting that FL has become an increasingly popular topic in the machine learning community in recent years.

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles

6:30 AM

Opening Remarks

Shiqiang Wang

6:35 AM

Trustworthy Federated Learning

Bo Li

Video

6:53 AM

Trustworthy Federated Learning - Q&A

6:57 AM

Asynchronous Optimization: Delays, Stability, and the Impact of Data Heterogeneity

Konstantin Mishchenko

Video

7:15 AM

Asynchronous Optimization: Delays, Stability, and the Impact of Data Heterogeneity - Q&A

7:20 AM

Conditional Moment Alignment for Improved Generalization in Federated Learning

Jayanth Reddy Regatti ⋅ Songtao Lu ⋅ Abhishek Gupta ⋅ Ness Shroff

Video

7:30 AM

Mechanisms that Incentivize Data Sharing in Federated Learning

Sai Praneeth Karimireddy ⋅ Wenshuo Guo ⋅ Michael Jordan

Video

7:40 AM

Federated Learning with Online Adaptive Heterogeneous Local Models

Hanhan Zhou ⋅ Tian Lan ⋅ Guru Prasadh Venkataramani ⋅ Wenbo Ding

Video

7:50 AM

LightVeriFL: Lightweight and Verifiable Secure Federated Learning

Baturalp Buyukates ⋅ Jinhyun So ⋅ Hessam Mahdavifar ⋅ Salman Avestimehr

Video

8:00 AM

Break

8:30 AM

Efficient Federated Random Subnetwork Training

Francesco Pase ⋅ Berivan Isik ⋅ Deniz Gunduz ⋅ Tsachy Weissman ⋅ Michele Zorzi

Video

8:40 AM

Group privacy for personalized federated learning

Filippo Galli ⋅ Sayan Biswas ⋅ Gangsoo Zeong ⋅ Tommaso Cucinotta ⋅ Catuscia Palamidessi

Video

8:50 AM

To Federate or Not To Federate: Incentivizing Client Participation in Federated Learning

Yae Jee Cho ⋅ Divyansh Jhunjhunwala ⋅ Tian Li ⋅ Virginia Smith ⋅ Gauri Joshi

Video

9:00 AM

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

Marco Bornstein ⋅ Tahseen Rabbani ⋅ Evan Wang ⋅ Amrit Bedi ⋅ Furong Huang

Video

9:10 AM

Best Paper Announcement

Video

9:15 AM

Poster Session 1

10:00 AM

Lunch Break

11:30 AM

FL Games: A Federated Learning Framework for Distribution Shifts

Sharut Gupta ⋅ Kartik Ahuja ⋅ Mohammad Havaei ⋅ Niladri Chatterjee ⋅ Yoshua Bengio

Video

11:40 AM

Verifiable Federated Machine Learning

Simone Bottoni ⋅ Giulio Zizzo ⋅ Stefano Braghin ⋅ Alberto Trombetta

Video

11:50 AM

Accelerated Federated Optimization with Quantization

Yeojoon Youn ⋅ Bhuvesh Kumar ⋅ Jacob Abernethy

Video

12:00 PM

Tackling Personalized Federated Learning with Label Concept Drift via Hierarchical Bayesian Modeling

Xingchen Ma ⋅ Junyi Zhu ⋅ Matthew Blaschko

Video

12:10 PM

Panel

Video

1:00 PM

Break

1:30 PM

On the Unreasonable Effectiveness of Federated Averaging with Heterogenous Data

Jianyu Wang

Video

1:48 PM

On the Unreasonable Effectiveness of Federated Averaging with Heterogenous Data - Q&A

1:52 PM

Scalable and Communication-Efficient Vertical Federated Learning

Stacy Patterson

Video

2:10 PM

Scalable and Communication-Efficient Vertical Federated Learning - Q&A

2:15 PM

Poster Session 2

FedTH : Tree-based Hierarchical Image Classification in Federated Learning

Jaeheon Kim ⋅ Bong Jun Choi

Unbounded Gradients in Federated Leaning with Buffered Asynchronous Aggregation

M. Taha Toghani ⋅ Cesar Uribe

Early Detection of Sexual Predators with Federated Learning

Khaoula Chehbouni ⋅ Gilles Caporossi ⋅ Reihaneh Rabbany ⋅ Martine De Cock ⋅ Golnoosh Farnadi

Self-Supervised Vertical Federated Learning

Timothy Castiglia ⋅ Shiqiang Wang ⋅ Stacy Patterson

On the Vulnerability of Backdoor Defenses for Federated Learning

Pei Fang ⋅ Jinghui Chen

Towards Provably Personalized Federated Learning via Threshold-Clustering of Similar Clients

Mariel A Werner ⋅ Lie He ⋅ Sai Praneeth Karimireddy ⋅ Michael Jordan ⋅ Martin Jaggi

Building Large Machine Learning Models from Small Distributed Models: A Layer Matching Approach

xinwei zhang ⋅ Bingqing Song ⋅ Mehrdad Honarkhah ⋅ Jie Ding ⋅ Mingyi Hong

VOTING-BASED APPROACHES FOR DIFFERENTIALLY PRIVATE FEDERATED LEARNING

Yuqing Zhu ⋅ Xiang Yu ⋅ Yi-Hsuan Tsai ⋅ Francesco Pittaluga ⋅ Masoud Faraki ⋅ Manmohan Chandraker ⋅ Yu-Xiang Wang

DASH: Decentralized CASH for Federated Learning

Md Ibrahim Ibne Alam ⋅ Koushik Kar ⋅ Theodoros Salonidis ⋅ Horst Samulowitz

Accelerating Adaptive Federated Optimization with Local Gossip Communications

Yujia Wang ⋅ Pei Fang ⋅ Jinghui Chen

Federated Progressive Sparsification (Purge-Merge-Tune)+

Dimitris Stripelis ⋅ Umang Gupta ⋅ Greg Ver Steeg ⋅ Jose-Luis Ambite

A Multi-Token Coordinate Descent Method for Vertical Federated Learning

Pedro Valdeira ⋅ Yuejie Chi ⋅ Claudia Soares ⋅ Joao Xavier

ColRel: Collaborative Relaying for Federated Learning over Intermittently Connected Networks

Rajarshi Saha ⋅ Michal Yemini ⋅ Emre Ozfatura ⋅ Deniz Gunduz ⋅ Andrea Goldsmith

Understanding Federated Learning through Loss Landscape Visualizations: A Pilot Study

Ziwei Li ⋅ Hong-You Chen ⋅ Han Wei Shen ⋅ Wei-Lun Chao

Differentially Private Federated Quantiles with the Distributed Discrete Gaussian Mechanism

Krishna Pillutla ⋅ Yassine Laguel ⋅ Jérôme Malick ⋅ Zaid Harchaoui

Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout

Chen Dun ⋅ Mirian Hipolito Garcia ⋅ Dimitrios Dimitriadis ⋅ Christopher Jermaine ⋅ Anastasios Kyrillidis

FedGRec: Federated Graph Recommender System with Lazy Update of Latent Embeddings

Junyi Li ⋅ Heng Huang

Privacy-Preserving Data Filtering in Federated Learning Using Influence Approximation

Ljubomir Rokvic ⋅ Panayiotis Danassis ⋅ Boi Faltings

Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

John Nguyen ⋅ Jianyu Wang ⋅ Kshitiz Malik ⋅ Maziar Sanjabi ⋅ Mike Rabbat

Trusted Aggregation (TAG): Model Filtering Backdoor Defense In Federated Learning

Joseph Lavond ⋅ Minhao Cheng ⋅ Yao Li

Cross-device Federated Architecture Search

Stefanos Laskaridis ⋅ Javier Fernandez-Marques ⋅ Łukasz Dudziak

Client-Private Secure Aggregation for Privacy-Preserving Federated Learning

Parker Newton ⋅ Olivia Choudhury ⋅ Bill Horne ⋅ Vidya Ravipati ⋅ Divya Bhargavi ⋅ Ujjwal Ratan

Motley: Benchmarking Heterogeneity and Personalization in Federated Learning

Shanshan Wu ⋅ Tian Li ⋅ Zachary Charles ⋅ Yu Xiao ⋅ Ken Liu ⋅ Zheng Xu ⋅ Virginia Smith

Federated Learning for Predicting the Next Node in Action Flows

Daniel Lopes ⋅ João Nadkarni ⋅ Filipe Assunção ⋅ Miguel Lopes ⋅ Luís Rodrigues

The Interpolated MVU Mechanism For Communication-efficient Private Federated Learning

Chuan Guo ⋅ Kamalika Chaudhuri ⋅ Pierre STOCK ⋅ Mike Rabbat

Find Your Friends: Personalized Federated Learning with the Right Collaborators

Yi Sui ⋅ Junfeng Wen ⋅ Yenson Lau ⋅ Brendan Ross ⋅ Jesse Cresswell

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks

Saeed Vahidian ⋅ Mahdi Morafah ⋅ Chen Chen ⋅ Mubarak Shah ⋅ Bill Lin

Federated Fairness without Access to Demographics

Afroditi Papadaki ⋅ Natalia Martinez ⋅ Martin Bertran ⋅ Guillermo Sapiro ⋅ Miguel Rodrigues

FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulations

Mirian Hipolito Garcia ⋅ Andre Manoel ⋅ Daniel Madrigal ⋅ Robert Sim ⋅ Dimitrios Dimitriadis

Decentralized Learning with Random Walks and Communication-Efficient Adaptive Optimization

Aleksei Triastcyn ⋅ Matthias Reisser ⋅ Christos Louizos

Accelerating Federated Learning Through Attention on Local Model Updates

Parsa Assadi ⋅ Byung Hoon Ahn ⋅ Hadi Esmaeilzadeh

Federated Frank-Wolfe Algorithm

Ali Dadras ⋅ Karthik Prakhya ⋅ Alp Yurtsever

How to Combine Variational Bayesian Networks in Federated Learning

Atahan Özer ⋅ Kadir Burak Buldu ⋅ Abdullah Akgül ⋅ Gozde Unal

Stochastic Gradient Methods with Compressed Communication for Decentralized Saddle Point Problems

Chhavi Sharma ⋅ Vishnu Narayanan ⋅ Balamurugan Palaniappan

Refined Convergence and Topology Learning for Decentralized Optimization with Heterogeneous Data

Batiste Le bars ⋅ Aurélien Bellet ⋅ Marc Tommasi ⋅ Erick Lavoie ⋅ Anne-marie Kermarrec

AIMHI: Protecting Sensitive Data through Federated Co-Training

Amr Abourayya ⋅ Michael Kamp ⋅ Erman Ayday ⋅ Jens Kleesiek ⋅ Kanishka Rao ⋅ Geoffrey Webb ⋅ Bharat Rao

A Novel Model-Based Attribute Inference Attack in Federated Learning

ilias driouich ⋅ CHUAN XU ⋅ Giovanni Neglia ⋅ Frederic Giroire ⋅ Eoin Thomas

FedSHIBU: Federated Similarity-based Head Independent Body Update

Athul Sreemathy Raj ⋅ Irene Tenison ⋅ Kacem Khaled ⋅ Felipe de Magalhães ⋅ Athul Sreemathy Raj

Revisiting the Activation Function for Federated Image Classification

Jaewoo Shin ⋅ Taehyeon Kim ⋅ Se-Young Yun

Adaptive Sparse Federated Learning in Large Output Spaces via Hashing

Zhaozhuo Xu ⋅ Luyang Liu ⋅ Zheng Xu ⋅ Anshumali Shrivastava

FLARE: Federated Learning from Simulation to Real-World

Holger Roth ⋅ Yan Cheng ⋅ Yuhong Wen ⋅ Te-Chung (Isaac) Yang ⋅ Ziyue Xu ⋅ Yuan-Ting Hsieh ⋅ Kristopher Kersten ⋅ Ahmed Harouni ⋅ Can Zhao ⋅ Kevin Lu ⋅ Zhihong Zhang ⋅ Wenqi Li ⋅ Andriy Myronenko ⋅ Dong Yang ⋅ Sean Yang ⋅ Nicola Rieke ⋅ Abood Quraini ⋅ Chester Chen ⋅ Daguang Xu ⋅ Nic Ma ⋅ Prerna Dogra ⋅ Mona Flores ⋅ Andrew Feng

PerFedSI: A Framework for Personalized Federated Learning with Side Information

Liam Collins ⋅ Enmao Diao ⋅ Tanya Roosta ⋅ Jie Ding ⋅ Tao Zhang

FedSynth: Gradient Compression via Synthetic Data in Federated Learning

Shengyuan Hu ⋅ Jack Goetz ⋅ Kshitiz Malik ⋅ Hongyuan Zhan ⋅ Zhe Liu ⋅ Yue Liu

Personalized Multi-tier Federated Learning

Sourasekhar Banerjee ⋅ Alp Yurtsever ⋅ Monowar Bhuyan

FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution

Saeed Vahidian ⋅ Mahdi Morafah ⋅ Weijia Wang ⋅ Bill Lin

Private and Robust Federated Learning using Private Information Retrieval and Norm Bounding

Hamid Mozaffari ⋅ Virendra Marathe ⋅ Dave Dice

Reconciling Security and Communication Efficiency in Federated Learning

Karthik Prasad ⋅ Sayan Ghosh ⋅ Graham Cormode ⋅ Ilya Mironov ⋅ Ashkan Yousefpour ⋅ Pierre STOCK

FedToken: Tokenized Incentives for Data Contribution in Federated Learning

Shashi Raj Pandey ⋅ Lam Nguyen ⋅ Petar Popovski

Federated Continual Learning with Differentially Private Data Sharing

Giulio Zizzo ⋅ Ambrish Rawat ⋅ Naoise Holohan ⋅ Seshu Tirupathi

$z$-SignFedAvg: A unified sign-based stochastic compression for federated learning

Zhiwei Tang ⋅ Yanmeng Wang ⋅ Tsung-Hui Chang

Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information

Kiwan Maeng ⋅ Chuan Guo ⋅ Sanjay Kariyappa ⋅ G. Edward Suh

FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning

Yuanhao Xiong ⋅ Ruochen Wang ⋅ Minhao Cheng ⋅ Felix Yu ⋅ Cho-Jui Hsieh

With a Little Help from My Friend: Server-Aided Federated Learning with Partial Client Participation

Haibo Yang ⋅ Peiwen Qiu ⋅ Prashant Khanduri ⋅ Jia Liu

Federated Learning of Large Models at the Edge via Principal Sub-Model Training

Yue Niu ⋅ Saurav Prakash ⋅ Souvik Kundu ⋅ Sunwoo Lee ⋅ Salman Avestimehr

FedRule: Federated Rule Recommendation System with Graph Neural Networks

Yuhang Yao ⋅ Mohammad Mahdi Kamani ⋅ Zhongwei Cheng ⋅ Lin Chen ⋅ Carlee Joe-Wong ⋅ Tianqiang Liu

Improving Vertical Federated Learning by Efficient Communication with ADMM

Chulin Xie ⋅ Pin-Yu Chen ⋅ Ce Zhang ⋅ Bo Li

Subject Level Differential Privacy with Hierarchical Gradient Averaging

Virendra Marathe ⋅ Pallika Kanani ⋅ Daniel Peterson

MocoSFL: enabling cross-client collaborative self-supervised learning

Jingtao Li ⋅ Lingjuan Lyu ⋅ Daisuke Iso ⋅ Chaitali Chakrabarti ⋅ Michael Spranger

Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing

Marco Schreyer ⋅ Hamed Hemati ⋅ Damian Borth ⋅ Miklos Vasarhelyi

Certified Robustness in Federated Learning

Motasem Alfarra ⋅ Juan Perez ⋅ Egor Shulgin ⋅ Peter Richtarik ⋅ Bernard Ghanem

Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge

Sara Babakniya ⋅ Souvik Kundu ⋅ Saurav Prakash ⋅ Yue Niu ⋅ Salman Avestimehr

Asynchronous speedup in decentralized optimization

Mathieu Even ⋅ Hadrien Hendrikx ⋅ Laurent Massoulié