Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data. However, D-SSL faces the critical challenge of data heterogeneity, and there is limited theoretical understanding of how different D-SSL frameworks respond to this challenge. To fill this gap, we present a rigorous theoretical analysis of the robustness of D-SSL frameworks under non-IID (non-independent and identically distributed) settings. Our results show that pre-training with Masked Image Modeling (MIM) is inherently more robust to heterogeneous
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorXuanyu Chen →
Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
- Linked via arxiv authorNan Yang →
Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
- Linked via arxiv authorShuai Wang →
Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data
- Linked via arxiv authorDong Yuan →
Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data