Timezone: »

 
Keynote Talk: Fair or Robust: Addressing Competing Constraints in Federated Learning (Virginia Smith)
Virginia Smith

Mon Dec 13 10:00 AM -- 10:45 AM (PST) @
in New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership »
Event URL: https://neurips2021workshopfl.github.io/NFFL-2021/schedule.html »

A defining trait of federated learning is the presence of heterogeneity, i.e., that data may differ significantly across the network. In this talk I discuss how heterogeneity affects issues of fairness and robustness in federated settings. Our work demonstrates that robustness to data/model poisoning attacks and fairness, measured as the uniformity of performance across devices, are constraints that can directly compete when training in heterogeneous networks. I then explore to what extent methods for personalized federated learning can mitigate the tension between these constraints. I end with promising directions of future work in personalization, fairness, and robustness for FL.

Author Information

Virginia Smith (Carnegie Mellon University)

More from the Same Authors