Timezone: »

 
Spotlight
VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?
Jiawei Jiang · Lukas Burkhalter · Fangcheng Fu · Bolin Ding · Bo Du · Anwar Hithnawi · Bo Li · Ce Zhang

Tue Dec 06 09:00 AM -- 11:00 AM (PST) @
in Lightning Talks 1A-3 »

Vertical Federated Learning (VFL), that trains federated models over vertically partitioned data, has emerged as an important learning paradigm. However, existing VFL methods are facing two challenges: (1) scalability when # participants grows to even modest scale and (2) diminishing return w.r.t. # participants: not all participants are equally important and many will not introduce quality improvement in a large consortium. Inspired by these two challenges, in this paper, we ask: How can we select l out of m participants, where l ≪ m, that are most important?We call this problem Vertically Federated Participant Selection, and model it with a principled mutual information-based view. Our first technical contribution is VF-MINE—a Vertically Federated Mutual INformation Estimator—that uses one of the most celebrated algorithms in database theory—Fagin’s algorithm as a building block. Our second contribution is to further optimize VF-MINE to enable VF-PS, a group testing-based participant selection framework. We empirically show that vertically federated participation selection can be orders of magnitude faster than training a full-fledged VFL model, while being able to identify the most important subset of participants that often lead to a VFL model of similar quality.

Keywords: Mutual Information · Vertical federated learning · participant selection · participant valuation

Author Information

Jiawei Jiang (Wuhan University)

Jiawei Jiang is a professor in School of Computer Science of Wuhan University. He obtained his Ph.D in Computer Science from Peking University in 2018. He worked as a postdoc researcher at ETH Zürich from 2019 to 2022. His research interests include, but are not limited to, machine learning systems, large-scale data analytics, graph processing, and federated learning. He has published more than 30 papers in top venues, e.g., SIGMOD, VLDB, ICDE, ICML, and NeurIPS.

Lukas Burkhalter (ETH Zurich)
Fangcheng Fu (Peking University)
Bolin Ding (Alibaba Group)
Bo Du (Wuhan University)
Anwar Hithnawi (ETHZ - ETH Zurich)
Bo Li (UIUC)
Ce Zhang (ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors