Skip to yearly menu bar Skip to main content


( events)   Timezone:  
Workshop
Fri Jul 28 12:00 PM -- 08:00 PM (PDT) @ Meeting Room 311 None
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





Workshop Home Page

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

Introduction and Opening Remarks (opening)
Vojta Jina: Lessons from Applying Private Federated Learning (Invited Talk)
Two Spotlight Talks (Spotlight Talks)
Break
Li Xiong: Federated Learning with Personalized and User-level Differential Privacy (Invited Talk)
Brendan McMahan: Advances in Privacy and Federated Learning, with Applications to GBoard (Invited Talk)
Poster and Lunch (Poster)
Panel Discussion (Panel)
Ce Zhang: Optimizing Communications and Data for Distributed and Decentralized Learning (Invited Talk)
Break
Giulia Fanti: New Variants of Old Challenges in Data Valuation and Privacy (Invited Talk)
Three Spotlight Talks (Spotlight Talks)
Chuan Guo: Towards (Truly) Private and Communication-efficient Federated Learning (Invited Talk)
Concluding Remarks (Concluding)
Towards a Better Theoretical Understanding of Independent Subnetwork Training (Poster)
Sketch-and-Project Meets Newton Method: \\ Global O(k2) Convergence with Low-Rank Updates (Poster)
A Convergent Federated Clustering Algorithm without Initial Condition (Poster)
Federated Conformal Predictors for Distributed Uncertainty Quantification (Poster)
Differentially Private Heavy Hitters using Federated Analytics (Poster)
ELF: Federated Langevin Algorithms with Primal, Dual and Bidirectional Compression (Poster)
SCAFF-PD: Communication Efficient Fair and Robust Federated Learning (Poster)
Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data (Poster)
Momentum Provably Improves Error Feedback! (Poster)
Federated Optimization Algorithms with Random Reshuffling and Gradient Compression (Poster)
Federated Learning with Regularized Client Participation (Poster)
Federated Ensemble-Directed Offline Reinforcement Learning (Poster)
Distributed Mean Estimation for Multi-Message Shuffled Privacy (Poster)
On Differentially Private Federated Linear Contextual Bandits (Poster)
Leveraging Side Information for Communication-Efficient Federated Learning (Poster)
Learning-augmented private algorithms for multiple quantile release (Poster)
A Joint Training-Calibration Framework for Test-Time Personalization with Label Distribution Shift in Federated Learning (Poster)
Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation (Poster)
Federated, Fast, and Private Visualization of Decentralized Data (Poster)
Adaptive Federated Learning with Auto-Tuned Clients (Poster)
Green Federated Learning (Poster)
Guiding The Last Layer in Federated Learning with Pre-Trained Models (Poster)
Exact Optimality in Communication-Privacy-Utility Tradeoffs (Poster)
Federated Heavy Hitter Recovery under Linear Sketching (Poster)
Improving Accelerated Federated Learning with Compression and Importance Sampling (Poster)
Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning (Poster)
Don’t Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory (Poster)
A New Theoretical Perspective on Data Heterogeneity in Federated Optimization (Poster)
FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning (Poster)
Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation (Poster)
Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration (Poster)
Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning (Poster)
Distributed Architecture Search over Heterogeneous Distributions (Poster)
Fast and Communication Efficient Decentralized Learning with Local Updates (Poster)
Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Information Theory (Poster)
Unleashing the Power of Randomization in Auditing Differentially Private ML (Poster)
FedFwd: Federated Learning without Backpropagation (Poster)
Federated Experiment Design under Distributed Differential Privacy (Poster)
Beyond Secure Aggregation: Scalable Multi-Round Secure Collaborative Learning (Poster)
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning (Poster)
Machine Learning with Feature Differential Privacy (Poster)
Towards a Theoretical and Practical Understanding of One-Shot Federated Learning with Fisher Information (Poster)
On the Still Unreasonable Effectiveness of Federated Averaging for Heterogeneous Distributed Learning (Poster)
Population Expansion for Training Language Models with Private Federated Learning (Poster)
Asynchronous Federated Learning with Bidirectional Quantized Communications and Buffered Aggregation (Poster)
Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data (Poster)
FED-CURE: A Robust Federated Learning Algorithm with Cubic Regularized Newton (Poster)
Resource-Efficient Federated Learning (Poster)
On the Performance of Gradient Tracking with Local Updates (Poster)
Privacy Auditing with One (1) Training Run (Poster)
Randomized Quantization is All You Need for Differential Privacy in Federated Learning (Poster)
Concept-aware clustering for decentralized deep learning under temporal shift (Poster)
Clustering-Guided Federated Learning of Representations (Poster)
Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning (Poster)
Strategic Data Sharing between Competitors (Poster)
Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes (Poster)