Unsupervised Multi-Source Federated Domain Adaptation under Domain Diversity through Group-Wise Discrepancy Minimization
This addresses the challenge of efficient and stable domain adaptation for privacy-sensitive applications with many diverse data sources, representing an incremental improvement over existing methods.
The paper tackles the problem of scaling unsupervised multi-source domain adaptation to many heterogeneous domains by proposing GALA, a federated framework that achieves competitive or state-of-the-art results on benchmarks and significantly outperforms prior methods in high-diversity settings.
Unsupervised multi-source domain adaptation (UMDA) aims to learn models that generalize to an unlabeled target domain by leveraging labeled data from multiple, diverse source domains. While distributed UMDA methods address privacy constraints by avoiding raw data sharing, existing approaches typically assume a small number of sources and fail to scale effectively. Increasing the number of heterogeneous domains often makes existing methods impractical, leading to high computational overhead or unstable performance. We propose GALA, a scalable and robust federated UMDA framework that introduces two key components: (1) a novel inter-group discrepancy minimization objective that efficiently approximates full pairwise domain alignment without quadratic computation; and (2) a temperature-controlled, centroid-based weighting strategy that dynamically prioritizes source domains based on alignment with the target. Together, these components enable stable and parallelizable training across large numbers of heterogeneous sources. To evaluate performance in high-diversity scenarios, we introduce Digit-18, a new benchmark comprising 18 digit datasets with varied synthetic and real-world domain shifts. Extensive experiments show that GALA consistently achieves competitive or state-of-the-art results on standard benchmarks and significantly outperforms prior methods in diverse multi-source settings where others fail to converge.