Skip to yearly menu bar Skip to main content


Poster

Federated Learning under Distributed Concept Drift

Ellango Jothimurugesan · Kevin Hsieh · Jianyu Wang · Gauri Joshi · Phillip B Gibbons

Auditorium 1 Foyer 32

Abstract:

Federated Learning (FL) under distributed concept drift is a largely unexplored area. Although concept drift is itself a well-studied phenomenon, it poses particular challenges for FL, because drifts arise staggered in time and space (across clients). Our work is the first to explicitly study data heterogeneity in both dimensions. We first demonstrate that prior solutions to drift adaptation, with their single global model, are ill-suited to staggered drifts, necessitating multiple-model solutions. We identify the problem of drift adaptation as a time-varying clustering problem, and we propose two new clustering algorithms for reacting to drifts based on local drift detection and hierarchical clustering. Empirical evaluation shows that our solutions achieve significantly higher accuracy than existing baselines, and are comparable to an idealized algorithm with oracle knowledge of the ground-truth clustering of clients to concepts at each time step.

Live content is unavailable. Log in and register to view live content