In collaborative learning, learners coordinate to enhance each of their learning performances. From the perspective of any learner, a critical challenge is to filter out unqualified collaborators. We propose a framework named meta clustering to address the challenge. Unlike the classical problem of clustering data points, meta clustering categorizes learners. Assuming each learner performs a supervised regression on a standalone local dataset, we propose a Select-Exchange-Cluster (SEC) method to classify the learners by their underlying supervised functions. We theoretically show that the SEC can cluster learners into accurate collaboration sets. Empirical studies corroborate the theoretical analysis and demonstrate that SEC can be computationally efficient, robust against learner heterogeneity, and effective in enhancing single-learner performance. Also, we show how the proposed approach may be used to enhance data fairness. Supplementary materials for this article are available online.
|Number of pages
|Journal of Computational and Graphical Statistics
|Published - 2023
Bibliographical noteFunding Information:
This article is based upon work supported by the National Science Foundation under grant number ECCS-2038603. We thank the anonymous reviewers and Editor for their valuable time and comments, which have helped us improve the original manuscript.
© 2022 American Statistical Association and Institute of Mathematical Statistics.
- Data integration
- Distributed computing
- Meta clustering
ASJC Scopus subject areas
- Discrete Mathematics and Combinatorics
- Statistics and Probability
- Statistics, Probability and Uncertainty