The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
Federated Generalized Category Discovery via Personalized Contrastive Graph Learning
- Published
- Record updated
Summary
The paper studies Federated Generalized Category Discovery (Fed-GCD), where clients collaborate privately to cluster unlabeled samples from known and unknown classes. It proposes Personalized Contrastive Graph Learning (PCGL), which separates generic and personalized knowledge, using a KNN-Former for local-graph contrastive learning and adaptive parameter masking with personalized aggregation. On six datasets, PCGL outperforms state-of-the-art methods, with a 4.8% average gain on All ACC for long-tailed natural and medical image datasets.