Skip to yearly menu bar Skip to main content


( events)   Timezone:  
Workshop
Mon Dec 13 05:30 AM -- 04:00 PM (PST)
New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership
Nghia Hoang · Lam Nguyen · Pin-Yu Chen · Tsui-Wei Weng · Sara Magliacane · Bryan Kian Hsiang Low · Anoop Deoras





Workshop Home Page

Federated Learning (FL) has recently emerged as the de facto framework for distributed machine learning (ML) that preserves the privacy of data, especially in the proliferation of mobile and edge devices with their increasing capacity for storage and computation. To fully utilize the vast amount of geographically distributed, diverse and privately owned data that is stored across these devices, FL provides a platform on which local devices can build their own local models whose training processes can be synchronized via sharing differential parameter updates. This was done without exposing their private training data, which helps mitigate the risk of privacy violation, in light of recent policies such as the General Data Protection Regulation (GDPR). Such potential use of FL has since then led to an explosive attention from the ML community resulting in a vast, growing amount of both theoretical and empirical literature that push FL so close to being the new standard of ML as a democratized data analytic service.

Interestingly, as FL comes closer to being deployable in real-world scenarios, it also surfaces a growing set of challenges on trustworthiness, fairness, auditability, scalability, robustness, security, privacy preservation, decentralizability, data ownership and personalizability that are all becoming increasingly important in many interrelated aspects of our digitized society. Such challenges are particularly important in economic landscapes that do not have the presence of big tech corporations with big data and are instead driven by government agencies and institutions with valuable data locked up or small-to-medium enterprises & start-ups with limited data and little funding. With this forethought, the workshop envisions the establishment of an AI ecosystem that facilitates data and model sharing between data curators as well as interested parties in the data and models while protecting personal data ownership.

Poster Session: [ protected link dropped ]

Pre-workshop networking (Networking Session)
Opening Remark
Keynote Talk: Building a New Economy: Federated Learning and Beyond (Alex Pentland) (Keynote Talk)
Q&A with Professor Alex Pentland (Q/A Live Session)
Contributed Talk 1: Personalized Neural Architecture Search for Federated Learning (Contributed Talk)
Contributed Talk 1 - Q/A Live session (Q/A Live session)
Contributed Talk 2: A Unified Framework to Understand Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective (Contributed Talk)
Contributed Talk 2 - Q/A Live session (Q/A Live session)
Contributed Talk 3: Architecture Personalization in Resource-constrained Federated Learning (Contributed Talk)
Contributed Talk 3 - Q/A Live Session (Q/A Live Session)
Keynote Talk: Permutation Compressors for Provably Faster Distributed Nonconvex Optimization (Peter Richtarik) (Keynote Talk)
Q&A with Professor Peter Richtarik (Q/A Live Session)
Keynote Talk: Bringing Differential Private SGD to Practice: On the Independence of Gaussian Noise and the Number of Training Rounds (Marten van Dijk) (Keynote Talk)
Q&A with Dr. Marten van Dijk (Q/A Live Session)
Lunch Break
Keynote Talk: Fair or Robust: Addressing Competing Constraints in Federated Learning (Virginia Smith) (Keynote Talk)
Q&A with A/Professor Virginia Smith (Q/A Live Session)
Contributed Talk 4: Sharp Bounds for FedAvg (Local SGD) (Contributed Talk)
Contributed Talk 4 - Q/A Live Session (Q/A Live Session)
Contributed Talk 5: Efficient and Private Federated Learning with Partially Trainable Networks (Contributed Talk)
Contributed Talk 5 - Q/A Live Session (Q/A Live Session)
Contributed Talk 6: FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning (Contributed Talk)
Contributed Talk 6 - Q/A Live Session (Q/A Live Session)
Poster Session
Keynote Talk: Towards Building a Responsible Data Economy (Dawn Song) (Keynote Talk)
Q&A with Professor Dawn Song (Q/A Live Session)
Keynote Talk: Personalization in Federated Learning: Adaptation and Clustering (Asu Ozdaglar) (Keynote Talk)
Q&A with Professor Asu Ozdaglar (Q/A Live Session)
Post-workshop Networking (Networking Session)
Closing Remark
Certified Federated Adversarial Training (Poster)
Certified Robustness for Free in Differentially Private Federated Learning (Poster)
FedMix: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning (Poster)
Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer (Poster)
FeO2: Federated Learning with Opt-Out Differential Privacy (Poster)
RVFR: Robust Vertical Federated Learning via Feature Subspace Recovery (Poster)
FedHist: A Federated-First Dataset for Learning in Healthcare (Poster)
Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning (Poster)
WAFFLE: Weighted Averaging for Personalized Federated Learning (Poster)
Decentralized Personalized Federated Min-Max Problems (Poster)
Secure Aggregation for Buffered Asynchronous Federated Learning (Poster)
Advanced Free-rider Attacks in Federated Learning (Poster)
CosSGD: Communication-Efficient Federated Learning with a Simple Cosine-Based Quantization (Poster)
Iterated Vector Fields and Conservatism, with Applications to Federated Learning (Poster)
Scalable Average Consensus with Compressed Communications (Poster)
FedJAX: Federated learning simulation with JAX (Poster)
Minimal Model Structure Analysis for Input Reconstruction in Federated Learning (Poster)
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses (Poster)
FedBABU: Towards Enhanced Representation for Federated Image Classification (Poster)
Bayesian SignSGD Optimizer for Federated Learning (Poster)
Learning Federated Representations and Recommendations with Limited Negatives (Poster)
What Do We Mean by Generalization in Federated Learning? (Poster)
FLoRA: Single-shot Hyper-parameter Optimization for Federated Learning (Poster)
Robust and Personalized Federated Learning with Spurious Features: an Adversarial Approach (Poster)
Detecting Poisoning Nodes in Federated Learning by Ranking Gradients (Poster)
Federating for Learning Group Fair Models (Poster)
Architecture Personalization in Resource-constrained Federated Learning (Poster)
Personalized Neural Architecture Search for Federated Learning (Poster)
Efficient and Private Federated Learning with Partially Trainable Networks (Poster)
Sharp Bounds for FedAvg (Local SGD) (Poster)
FairFed: Enabling Group Fairness in Federated Learning (Poster)
Secure Byzantine-Robust Distributed Learning via Clustering (Poster)
Contribution Evaluation in Federated Learning: Examining Current Approaches (Poster)
Bayesian Framework for Gradient Leakage (Poster)
FedRAD: Federated Robust Adaptive Distillation (Poster)
FedGMA: Federated Learning with Gradient Masked Averaging (Poster)
A Unified Framework to Understand Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective (Poster)