pith. sign in

arxiv: 2409.10720 · v2 · pith:RTXBJGQ3new · submitted 2024-09-16 · 💻 cs.LG

On the effects of similarity metrics in decentralized deep learning under distributional shift

classification 💻 cs.LG
keywords metricslearningcollaborationdatadecentralizeddeepidentifyingmodel
0
0 comments X
read the original abstract

Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.