Timezone: »

Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks
Saeed Vahidian · Mahdi Morafah · Chen Chen · Mubarak Shah · Bill Lin
Event URL: https://openreview.net/forum?id=2mQCv0_Ac74 »

Though successful, federated learning presents new challenges for machine learning, especially when the issue of data heterogeneity, also known as Non-IID data, arises. To cope with the statistical heterogeneity, previous works incorporated a proximal term in local optimization or modified the model aggregation scheme at the server side or advocated clustered federated learning approaches where the central server groups agent population into clusters with jointly trainable data distributions to take the advantage of a certain level of personalization. While effective, they lack a deep elaboration on what kind of data heterogeneity and how the data heterogeneity impacts the accuracy performance of the participating clients. In contrast to many of the prior federated learning approaches, we demonstrate not only the issue of data heterogeneity in current setups is not necessarily a problem but also in fact it can be beneficial for the FL participants. Our observations are intuitive: (1) Dissimilar labels of clients (label skew) are not necessarily considered data heterogeneity, and (2) the principal angle between the agents' data subspaces spanned by their corresponding principal vectors of data is a better estimate of the data heterogeneity.

Author Information

Saeed Vahidian (University of California, San Diego)
Mahdi Morafah (University of California, San Diego)
Chen Chen (University of Central Florida)
Mubarak Shah (University of Central Florida)
Bill Lin (University of California, San Diego)

More from the Same Authors