Skip to yearly menu bar Skip to main content

Workshop

Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities

Zheng Xu ⋅ Peter Kairouz ⋅ Bo Li ⋅ Tian Li ⋅ John Nguyen ⋅ Jianyu Wang ⋅ Shiqiang Wang ⋅ Ayfer Ozgur

Project Page

Abstract

Proposed around 2016 as privacy preserving techniques, federated learning and analytics (FL & FA) made remarkable progress in theory and practice in recent years. However, there is a growing disconnect between theoretical research and practical applications of federated learning. This workshop aims to bring academics and practitioners closer together to exchange ideas: discuss actual systems and practical applications to inspire researchers to work on theoretical and practical research questions that lead to real-world impact; understand the current development and highlight future directions. To achieve this goal, we aim to have a set of keynote talks and panelists by industry researchers focused on deploying federated learning and analytics in practice, and academic research leaders who are interested in bridging the gap between the theory and practice.

For more details, please visit the workshop webpage at https://fl-icml2023.github.io

Video

Chat is not available.

Schedule

Timezone: Asia/Seoul

4:00 AM

Introduction and Opening Remarks

Zheng Xu

Video

4:05 AM

Vojta Jina: Lessons from Applying Private Federated Learning

Video

4:40 AM

Two Spotlight Talks

Video

5:00 AM

Break

Video

5:15 AM

Li Xiong: Federated Learning with Personalized and User-level Differential Privacy

Li Xiong

5:50 AM

Brendan McMahan: Advances in Privacy and Federated Learning, with Applications to GBoard

Brendan McMahan

Video

6:25 AM

Poster and Lunch

8:30 AM

Panel Discussion

Peter Kairouz ⋅ Song Han ⋅ Kamalika Chaudhuri ⋅ Florian Tramer

Video

9:25 AM

Ce Zhang: Optimizing Communications and Data for Distributed and Decentralized Learning

10:00 AM

Break

10:15 AM

Giulia Fanti: New Variants of Old Challenges in Data Valuation and Privacy

Video

10:50 AM

Three Spotlight Talks

Video

11:20 AM

Chuan Guo: Towards (Truly) Private and Communication-efficient Federated Learning

Video

11:55 AM

Concluding Remarks

On the Still Unreasonable Effectiveness of Federated Averaging for Heterogeneous Distributed Learning

Kumar Kshitij Patel ⋅ Margalit Glasgow ⋅ Lingxiao Wang ⋅ Nirmit Joshi ⋅ Nati Srebro

Towards a Theoretical and Practical Understanding of One-Shot Federated Learning with Fisher Information

Divyansh Jhunjhunwala ⋅ Shiqiang Wang ⋅ Gauri Joshi

Machine Learning with Feature Differential Privacy

Saeed Mahloujifar ⋅ Chuan Guo ⋅ G. Edward Suh ⋅ Kamalika Chaudhuri

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

Kostadin Garov ⋅ Dimitar I. Dimitrov ⋅ Nikola Jovanović ⋅ Martin Vechev

Beyond Secure Aggregation: Scalable Multi-Round Secure Collaborative Learning

Umit Basaran ⋅ Xingyu Lu ⋅ Basak Guler

Federated Experiment Design under Distributed Differential Privacy

Wei-Ning Chen ⋅ Graham Cormode ⋅ Akash Bharadwaj ⋅ Peter Romov ⋅ Ayfer Ozgur

FedFwd: Federated Learning without Backpropagation

Seonghwan Park ⋅ Dahun Shin ⋅ Jinseok Chung ⋅ Namhoon Lee

Unleashing the Power of Randomization in Auditing Differentially Private ML

Krishna Pillutla ⋅ Galen Andrew ⋅ Peter Kairouz ⋅ Hugh B McMahan ⋅ Alina Oprea ⋅ Sewoong Oh

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Information Theory

Faisal Hamman ⋅ Sanghamitra Dutta

Fast and Communication Efficient Decentralized Learning with Local Updates

Peyman Gholami ⋅ Hulya Seferoglu

Distributed Architecture Search over Heterogeneous Distributions

Erum Mushtaq ⋅ Chaoyang He ⋅ Jie Ding ⋅ Salman Avestimehr

Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning

Gwen Legate ⋅ Lucas Caccia ⋅ Eugene Belilovsky

Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration

Yujia Wang ⋅ Yuanpu Cao ⋅ Jingcheng Wu ⋅ Ruoyu Chen ⋅ Jinghui Chen

Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation

Wei-Ning Chen ⋅ Dan Song ⋅ Ayfer Ozgur ⋅ Peter Kairouz

FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning

Rishub Tamirisa ⋅ John Won ⋅ Chengjun Lu ⋅ Ron Arel ⋅ Andy Zhou

A New Theoretical Perspective on Data Heterogeneity in Federated Optimization

Jiayi Wang ⋅ Shiqiang Wang ⋅ Rong-Rong Chen ⋅ Mingyue Ji

Don’t Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory

Sara Babakniya ⋅ Zalan Fabian ⋅ Chaoyang He ⋅ Mahdi Soltanolkotabi ⋅ Salman Avestimehr

Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning

GAURAV BAGWE ⋅ Xiaoyong Yuan ⋅ Miao Pan ⋅ Lan Zhang

Improving Accelerated Federated Learning with Compression and Importance Sampling

Michał Grudzień ⋅ Grigory Malinovsky ⋅ Peter Richtarik

Federated Heavy Hitter Recovery under Linear Sketching

Adria Gascon ⋅ Peter Kairouz ⋅ Ziteng Sun ⋅ Ananda Suresh

Exact Optimality in Communication-Privacy-Utility Tradeoffs

Berivan Isik ⋅ Wei-Ning Chen ⋅ Ayfer Ozgur ⋅ Tsachy Weissman ⋅ Albert No

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Gwen Legate ⋅ Nicolas Bernier ⋅ Lucas Caccia ⋅ Edouard Oyallon ⋅ Eugene Belilovsky

Green Federated Learning

Ashkan Yousefpour ⋅ Shen Guo ⋅ Ashish Shenoy ⋅ Sayan Ghosh ⋅ Pierre Stock ⋅ Kiwan Maeng ⋅ Schalk-Willem Krüger ⋅ Michael Rabbat ⋅ Carole-Jean Wu ⋅ Ilya Mironov

Adaptive Federated Learning with Auto-Tuned Clients

J. Lyle Kim ⋅ Mohammad Taha Toghani ⋅ Cesar Uribe ⋅ Anastasios Kyrillidis

Federated, Fast, and Private Visualization of Decentralized Data

Debbrata Kumar Saha ⋅ Vince Calhoun ⋅ Soo Min Kwon ⋅ Anand Sarwate ⋅ Rekha Saha ⋅ Sergey Plis

Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation

Anbang Zhang ⋅ Shuaishuai Guo ⋅ Shuai Liu

A Joint Training-Calibration Framework for Test-Time Personalization with Label Distribution Shift in Federated Learning

Jian Xu ⋅ Shao-Lun Huang

Learning-augmented private algorithms for multiple quantile release

Mikhail Khodak ⋅ Kareem Amin ⋅ Travis Dick ⋅ Sergei Vassilvitskii

Leveraging Side Information for Communication-Efficient Federated Learning

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

On Differentially Private Federated Linear Contextual Bandits

Xingyu Zhou ⋅ Sayak Ray Chowdhury

Distributed Mean Estimation for Multi-Message Shuffled Privacy

Antonious Girgis ⋅ Suhas Diggavi

Federated Ensemble-Directed Offline Reinforcement Learning

Desik Rengarajan ⋅ Nitin Ragothaman ⋅ Dileep Kalathil ⋅ Srinivas Shakkottai

Federated Learning with Regularized Client Participation

Grigory Malinovsky ⋅ Samuel Horváth ⋅ Konstantin Burlachenko ⋅ Peter Richtarik

Federated Optimization Algorithms with Random Reshuffling and Gradient Compression

Abdurakhmon Sadiev ⋅ Grigory Malinovsky ⋅ Eduard Gorbunov ⋅ Igor Sokolov ⋅ Ahmed Khaled ⋅ Konstantin Burlachenko ⋅ Peter Richtarik

Momentum Provably Improves Error Feedback!

Ilyas Fatkhullin ⋅ Alexander Tyurin ⋅ Peter Richtarik

Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data

Jiaqi Shao ⋅ Shanshan Han ⋅ Chaoyang He ⋅ Bing Luo

SCAFF-PD: Communication Efficient Fair and Robust Federated Learning

Yaodong Yu ⋅ Sai Praneeth Karimireddy ⋅ Yi Ma ⋅ Michael Jordan

ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression

Avetik Karagulyan ⋅ Peter Richtarik

Differentially Private Heavy Hitters using Federated Analytics

Karan Chadha ⋅ Junye Chen ⋅ John Duchi ⋅ Vitaly Feldman ⋅ Hanieh Hashemi ⋅ Omid Javidbakht ⋅ Audra McMillan ⋅ Kunal Talwar

Federated Conformal Predictors for Distributed Uncertainty Quantification

Charles Lu ⋅ Yaodong Yu ⋅ Sai Praneeth Karimireddy ⋅ Michael Jordan ⋅ Ramesh Raskar

A Convergent Federated Clustering Algorithm without Initial Condition

Harsh Vardhan ⋅ Avishek Ghosh ⋅ Arya Mazumdar

Sketch-and-Project Meets Newton Method: \\ Global $\mathcal O \left( k^{-2} \right)$ Convergence with Low-Rank Updates

Slavomír Hanzely

Towards a Better Theoretical Understanding of Independent Subnetwork Training

Egor Shulgin ⋅ Peter Richtarik

Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes

Konstantin Mishchenko ⋅ Slavomír Hanzely ⋅ Peter Richtarik

Strategic Data Sharing between Competitors

Nikita Tsoy ⋅ Nikola Konstantinov

Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning

Baihe Huang ⋅ Sai Praneeth Karimireddy ⋅ Michael Jordan

Clustering-Guided Federated Learning of Representations

Runxuan Miao ⋅ Erdem Koyuncu

Concept-aware clustering for decentralized deep learning under temporal shift

Edvin Listo Zec ⋅ Emilie Klefbom ⋅ Marcus Toftås ⋅ Martin Willbo ⋅ Olof Mogren

Randomized Quantization is All You Need for Differential Privacy in Federated Learning

Yeojoon Youn ⋅ Zihao Hu ⋅ Juba Ziani ⋅ Jacob Abernethy

Privacy Auditing with One (1) Training Run

Thomas Steinke ⋅ Milad Nasresfahani ⋅ Matthew Jagielski

On the Performance of Gradient Tracking with Local Updates

Edward Duc Hien Nguyen ⋅ Sulaiman Alghunaim ⋅ Kun Yuan ⋅ Cesar Uribe

Resource-Efficient Federated Learning

Ahmed M. Abdelmoniem ⋅ Atal Sahu ⋅ Marco Canini ⋅ Suhaib Fahmy

$\texttt{FED-CURE}$: A Robust Federated Learning Algorithm with Cubic Regularized Newton

Avishek Ghosh ⋅ Raj Kumar Maity ⋅ Arya Mazumdar

Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data

Sai Aparna Aketi ⋅ Sangamesh Kodge ⋅ Kaushik Roy

Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation

Tomas Ortega ⋅ Hamid Jafarkhani

Population Expansion for Training Language Models with Private Federated Learning

Tatsuki Koga ⋅ Congzheng Song ⋅ Martin Pelikan ⋅ Mona Chitnis