Gains: Fine-grained Federated Domain Adaptation in Open Set
This addresses the practical challenge of open-set federated learning where new clients introduce domain shifts, though it appears incremental as it builds on existing encoder-classifier splits and aggregation techniques.
The paper tackles the problem of federated learning with continuously joining clients by proposing Gains, a fine-grained federated domain adaptation approach that detects and integrates new knowledge while preserving source domain performance. Experimental results show it significantly outperforms baselines in both source and target domains across multiple data-shift scenarios.
Conventional federated learning (FL) assumes a closed world with a fixed total number of clients. In contrast, new clients continuously join the FL process in real-world scenarios, introducing new knowledge. This raises two critical demands: detecting new knowledge, i.e., knowledge discovery, and integrating it into the global model, i.e., knowledge adaptation. Existing research focuses on coarse-grained knowledge discovery, and often sacrifices source domain performance and adaptation efficiency. To this end, we propose a fine-grained federated domain adaptation approach in open set (Gains). Gains splits the model into an encoder and a classifier, empirically revealing features extracted by the encoder are sensitive to domain shifts while classifier parameters are sensitive to class increments. Based on this, we develop fine-grained knowledge discovery and contribution-driven aggregation techniques to identify and incorporate new knowledge. Additionally, an anti-forgetting mechanism is designed to preserve source domain performance, ensuring balanced adaptation. Experimental results on multi-domain datasets across three typical data-shift scenarios demonstrate that Gains significantly outperforms other baselines in performance for both source-domain and target-domain clients. Code is available at: https://github.com/Zhong-Zhengyi/Gains.