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
Meeting Room 311
Fri 28 Jul, noon PDT
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
Schedule
Fri 12:00 p.m. - 12:05 p.m.
|
Introduction and Opening Remarks
(
opening
)
>
SlidesLive Video |
Zheng Xu 🔗 |
Fri 12:05 p.m. - 12:40 p.m.
|
Vojta Jina: Lessons from Applying Private Federated Learning
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Fri 12:40 p.m. - 1:00 p.m.
|
Two Spotlight Talks
(
Spotlight Talks
)
>
SlidesLive Video |
🔗 |
Fri 1:00 p.m. - 1:15 p.m.
|
Break
|
🔗 |
Fri 1:15 p.m. - 1:50 p.m.
|
Li Xiong: Federated Learning with Personalized and User-level Differential Privacy
(
Invited Talk
)
>
SlidesLive Video |
Li Xiong 🔗 |
Fri 1:50 p.m. - 2:25 p.m.
|
Brendan McMahan: Advances in Privacy and Federated Learning, with Applications to GBoard
(
Invited Talk
)
>
SlidesLive Video |
Brendan McMahan 🔗 |
Fri 2:25 p.m. - 4:30 p.m.
|
Poster and Lunch
(
Poster
)
>
|
🔗 |
Fri 4:30 p.m. - 5:25 p.m.
|
Panel Discussion
(
Panel
)
>
SlidesLive Video |
Peter Kairouz · Song Han · Kamalika Chaudhuri · Florian Tramer 🔗 |
Fri 5:25 p.m. - 6:00 p.m.
|
Ce Zhang: Optimizing Communications and Data for Distributed and Decentralized Learning
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Fri 6:00 p.m. - 6:15 p.m.
|
Break
|
🔗 |
Fri 6:15 p.m. - 6:50 p.m.
|
Giulia Fanti: New Variants of Old Challenges in Data Valuation and Privacy
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Fri 6:50 p.m. - 7:20 p.m.
|
Three Spotlight Talks
(
Spotlight Talks
)
>
SlidesLive Video |
🔗 |
Fri 7:20 p.m. - 7:55 p.m.
|
Chuan Guo: Towards (Truly) Private and Communication-efficient Federated Learning
(
Invited Talk
)
>
SlidesLive Video |
🔗 |
Fri 7:55 p.m. - 8:00 p.m.
|
Concluding Remarks
(
Concluding
)
>
SlidesLive Video |
🔗 |
-
|
On the Still Unreasonable Effectiveness of Federated Averaging for Heterogeneous Distributed Learning ( Poster ) > link | 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 ( Poster ) > link | Divyansh Jhunjhunwala · Shiqiang Wang · Gauri Joshi 🔗 |
-
|
Machine Learning with Feature Differential Privacy ( Poster ) > link | Saeed Mahloujifar · Chuan Guo · G. Edward Suh · Kamalika Chaudhuri 🔗 |
-
|
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning ( Poster ) > link | Kostadin Garov · Dimitar I. Dimitrov · Nikola Jovanović · Martin Vechev 🔗 |
-
|
Beyond Secure Aggregation: Scalable Multi-Round Secure Collaborative Learning ( Poster ) > link | Umit Basaran · Xingyu Lu · Basak Guler 🔗 |
-
|
Federated Experiment Design under Distributed Differential Privacy ( Poster ) > link | Wei-Ning Chen · Graham Cormode · Akash Bharadwaj · Peter Romov · Ayfer Ozgur 🔗 |
-
|
FedFwd: Federated Learning without Backpropagation ( Poster ) > link | Seonghwan Park · Dahun Shin · Jinseok Chung · Namhoon Lee 🔗 |
-
|
Unleashing the Power of Randomization in Auditing Differentially Private ML ( Poster ) > link | 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 ( Poster ) > link | Faisal Hamman · Sanghamitra Dutta 🔗 |
-
|
Fast and Communication Efficient Decentralized Learning with Local Updates ( Poster ) > link | Peyman Gholami · Hulya Seferoglu 🔗 |
-
|
Distributed Architecture Search over Heterogeneous Distributions ( Poster ) > link | Erum Mushtaq · Chaoyang He · Jie Ding · Salman Avestimehr 🔗 |
-
|
Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning ( Poster ) > link | Gwen Legate · Lucas Caccia · Eugene Belilovsky 🔗 |
-
|
Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration ( Poster ) > link | 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 ( Poster ) > link | Wei-Ning Chen · Dan Song · Ayfer Ozgur · Peter Kairouz 🔗 |
-
|
FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning ( Poster ) > link | Rishub Tamirisa · John Won · Chengjun Lu · Ron Arel · Andy Zhou 🔗 |
-
|
A New Theoretical Perspective on Data Heterogeneity in Federated Optimization ( Poster ) > link | Jiayi Wang · Shiqiang Wang · Rong-Rong Chen · Mingyue Ji 🔗 |
-
|
Don’t Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory ( Poster ) > link | Sara Babakniya · Zalan Fabian · Chaoyang He · Mahdi Soltanolkotabi · Salman Avestimehr 🔗 |
-
|
Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning ( Poster ) > link | GAURAV BAGWE · Xiaoyong Yuan · Miao Pan · Lan Zhang 🔗 |
-
|
Improving Accelerated Federated Learning with Compression and Importance Sampling ( Poster ) > link | Michał Grudzień · Grigory Malinovsky · Peter Richtarik 🔗 |
-
|
Federated Heavy Hitter Recovery under Linear Sketching ( Poster ) > link | Adria Gascon · Peter Kairouz · Ziteng Sun · Ananda Suresh 🔗 |
-
|
Exact Optimality in Communication-Privacy-Utility Tradeoffs ( Poster ) > link | Berivan Isik · Wei-Ning Chen · Ayfer Ozgur · Tsachy Weissman · Albert No 🔗 |
-
|
Guiding The Last Layer in Federated Learning with Pre-Trained Models ( Poster ) > link | Gwen Legate · Nicolas Bernier · Lucas Caccia · Edouard Oyallon · Eugene Belilovsky 🔗 |
-
|
Green Federated Learning ( Poster ) > link | 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 ( Poster ) > link | J. Lyle Kim · Mohammad Taha Toghani · Cesar Uribe · Anastasios Kyrillidis 🔗 |
-
|
Federated, Fast, and Private Visualization of Decentralized Data ( Poster ) > link | 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 ( Poster ) > link | Anbang Zhang · Shuaishuai Guo · Shuai Liu 🔗 |
-
|
A Joint Training-Calibration Framework for Test-Time Personalization with Label Distribution Shift in Federated Learning ( Poster ) > link | Jian Xu · Shao-Lun Huang 🔗 |
-
|
Learning-augmented private algorithms for multiple quantile release ( Poster ) > link | Mikhail Khodak · Kareem Amin · Travis Dick · Sergei Vassilvitskii 🔗 |
-
|
Leveraging Side Information for Communication-Efficient Federated Learning ( Poster ) > link | Berivan Isik · Francesco Pase · Deniz Gunduz · Sanmi Koyejo · Tsachy Weissman · Michele Zorzi 🔗 |
-
|
On Differentially Private Federated Linear Contextual Bandits ( Poster ) > link | Xingyu Zhou · Sayak Ray Chowdhury 🔗 |
-
|
Distributed Mean Estimation for Multi-Message Shuffled Privacy ( Poster ) > link | Antonious Girgis · Suhas Diggavi 🔗 |
-
|
Federated Ensemble-Directed Offline Reinforcement Learning ( Poster ) > link | Desik Rengarajan · Nitin Ragothaman · Dileep Kalathil · Srinivas Shakkottai 🔗 |
-
|
Federated Learning with Regularized Client Participation ( Poster ) > link | Grigory Malinovsky · Samuel Horváth · Konstantin Burlachenko · Peter Richtarik 🔗 |
-
|
Federated Optimization Algorithms with Random Reshuffling and Gradient Compression ( Poster ) > link | Abdurakhmon Sadiev · Grigory Malinovsky · Eduard Gorbunov · Igor Sokolov · Ahmed Khaled · Konstantin Burlachenko · Peter Richtarik 🔗 |
-
|
Momentum Provably Improves Error Feedback! ( Poster ) > link | Ilyas Fatkhullin · Alexander Tyurin · Peter Richtarik 🔗 |
-
|
Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data ( Poster ) > link | Jiaqi Shao · Shanshan Han · Chaoyang He · Bing Luo 🔗 |
-
|
SCAFF-PD: Communication Efficient Fair and Robust Federated Learning ( Poster ) > link | Yaodong Yu · Sai Praneeth Karimireddy · Yi Ma · Michael Jordan 🔗 |
-
|
ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression ( Poster ) > link | Avetik Karagulyan · Peter Richtarik 🔗 |
-
|
Differentially Private Heavy Hitters using Federated Analytics ( Poster ) > link | Karan Chadha · Junye Chen · John Duchi · Vitaly Feldman · Hanieh Hashemi · Omid Javidbakht · Audra McMillan · Kunal Talwar 🔗 |
-
|
Federated Conformal Predictors for Distributed Uncertainty Quantification ( Poster ) > link | Charles Lu · Yaodong Yu · Sai Praneeth Karimireddy · Michael Jordan · Ramesh Raskar 🔗 |
-
|
A Convergent Federated Clustering Algorithm without Initial Condition ( Poster ) > link | Harsh Vardhan · Avishek Ghosh · Arya Mazumdar 🔗 |
-
|
Sketch-and-Project Meets Newton Method: \\ Global $\mathcal O \left( k^{-2} \right)$ Convergence with Low-Rank Updates ( Poster ) > link | Slavomír Hanzely 🔗 |
-
|
Towards a Better Theoretical Understanding of Independent Subnetwork Training ( Poster ) > link | Egor Shulgin · Peter Richtarik 🔗 |
-
|
Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes ( Poster ) > link | Konstantin Mishchenko · Slavomír Hanzely · Peter Richtarik 🔗 |
-
|
Strategic Data Sharing between Competitors ( Poster ) > link | Nikita Tsoy · Nikola Konstantinov 🔗 |
-
|
Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning ( Poster ) > link | Baihe Huang · Sai Praneeth Karimireddy · Michael Jordan 🔗 |
-
|
Clustering-Guided Federated Learning of Representations ( Poster ) > link | Runxuan Miao · Erdem Koyuncu 🔗 |
-
|
Concept-aware clustering for decentralized deep learning under temporal shift ( Poster ) > link | Edvin Listo Zec · Emilie Klefbom · Marcus Toftås · Martin Willbo · Olof Mogren 🔗 |
-
|
Randomized Quantization is All You Need for Differential Privacy in Federated Learning ( Poster ) > link | Yeojoon Youn · Zihao Hu · Juba Ziani · Jacob Abernethy 🔗 |
-
|
Privacy Auditing with One (1) Training Run ( Poster ) > link | Thomas Steinke · Milad Nasresfahani · Matthew Jagielski 🔗 |
-
|
On the Performance of Gradient Tracking with Local Updates ( Poster ) > link | Edward Duc Hien Nguyen · Sulaiman Alghunaim · Kun Yuan · Cesar Uribe 🔗 |
-
|
Resource-Efficient Federated Learning ( Poster ) > link | Ahmed M. Abdelmoniem · Atal Sahu · Marco Canini · Suhaib Fahmy 🔗 |
-
|
$\texttt{FED-CURE}$: A Robust Federated Learning Algorithm with Cubic Regularized Newton ( Poster ) > link | Avishek Ghosh · Raj Kumar Maity · Arya Mazumdar 🔗 |
-
|
Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data ( Poster ) > link | Sai Aparna Aketi · Sangamesh Kodge · Kaushik Roy 🔗 |
-
|
Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation ( Poster ) > link | Tomas Ortega · Hamid Jafarkhani 🔗 |
-
|
Population Expansion for Training Language Models with Private Federated Learning ( Poster ) > link | Tatsuki Koga · Congzheng Song · Martin Pelikan · Mona Chitnis 🔗 |