Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification

ArXi:2603.29633v1 Announce Type: new Label-scarce visual classification under decentralized and heterogeneous data is a fundamental challenge in pattern recognition, especially when sites exhibit partially overlapping class sets. While self-supervised federated learning (SSFL) offers a promising solution, existing studies commonly assume the same data heterogeneity pattern throughout pre-