Federated Learning under Distributed Concept Drift

06/01/2022
by   Ellango Jothimurugesan, et al.
0

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 multi-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.

READ FULL TEXT

page 3

page 9

page 16

research
04/27/2022

AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation

In Federated Learning (FL), a number of clients or devices collaborate t...
research
09/01/2021

Asynchronous Federated Learning for Sensor Data with Concept Drift

Federated learning (FL) involves multiple distributed devices jointly tr...
research
11/22/2022

Online Federated Learning via Non-Stationary Detection and Adaptation amidst Concept Drift

Federated Learning (FL) is an emerging domain in the broader context of ...
research
03/27/2021

Human-in-the-loop Handling of Knowledge Drift

We introduce and study knowledge drift (KD), a complex form of drift tha...
research
04/03/2022

A Computational Analysis of Pitch Drift in Unaccompanied Solo Singing using DBSCAN Clustering

Unaccompanied vocalists usually change the tuning unintentionally and en...
research
11/14/2021

Attentive Federated Learning for Concept Drift in Distributed 5G Edge Networks

Machine learning (ML) is expected to play a major role in 5G edge comput...

Please sign up or login with your details

Forgot password? Click here to reset