Abstract-only report: theoretical comparison finds MIM more robust than CL to non-IID data in D-SSL and robustness scales with connectivity; MAR loss proposed as practical application.
arXiv preprint arXiv:2210.10947 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
Abstract-only report: theoretical comparison finds MIM more robust than CL to non-IID data in D-SSL and robustness scales with connectivity; MAR loss proposed as practical application.