SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
This work addresses domain adaptation for machine learning applications where labeled data is scarce in target domains, offering an incremental improvement by integrating graph-based structures and spectral techniques.
The paper tackles the tradeoff between inter-domain transferability and intra-domain discriminability in domain adaptation by proposing SPA++, a generalized graph spectral alignment framework that incorporates spectral regularization and neighbor-aware propagation. It demonstrates superior performance over existing methods on benchmark datasets, achieving robust adaptability across various challenging scenarios.
Domain Adaptation (DA) aims to transfer knowledge from a labeled source domain to an unlabeled or sparsely labeled target domain under domain shifts. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. To tackle this tradeoff, we propose a generalized graph SPectral Alignment framework, SPA++. Its core is briefly condensed as follows: (1)-by casting the DA problem to graph primitives, it composes a coarse graph alignment mechanism with a novel spectral regularizer toward aligning the domain graphs in eigenspaces; (2)-we further develop a fine-grained neighbor-aware propagation mechanism for enhanced discriminability in the target domain; (3)-by incorporating data augmentation and consistency regularization, SPA++ can adapt to complex scenarios including most DA settings and even challenging distribution scenarios. Furthermore, we also provide theoretical analysis to support our method, including the generalization bound of graph-based DA and the role of spectral alignment and smoothing consistency. Extensive experiments on benchmark datasets demonstrate that SPA++ consistently outperforms existing cutting-edge methods, achieving superior robustness and adaptability across various challenging adaptation scenarios.