Meta Clustering for Collaborative Learning
This addresses the problem of improving collaboration efficiency and fairness in machine learning for learners with local datasets, though it appears incremental as it builds on existing collaborative learning concepts.
The paper tackles the challenge of filtering unqualified collaborators in collaborative learning by proposing a meta clustering framework that categorizes learners based on their underlying supervised functions, showing that it can cluster learners into accurate collaboration sets and enhance single-learner performance with computational efficiency and robustness against heterogeneity.
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.