通过谱对齐增强图结构，提升域自适应的泛化能力
SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
- 构建图谱对齐框架，利用谱正则化在特征空间对齐源与目标域
- 引入邻域感知传播机制，显著提升目标域的分类判别力
- 支持多种复杂分布场景，适合高鲁棒性需求的跨域应用
域自适应（DA）旨在将标注源域的知识迁移到未标注或稀疏标注的目标域中，应对领域偏移问题。现有方法多关注跨域可迁移性，却忽视了域内丰富结构，导致判别能力下降。为此，本文提出通用图谱对齐框架SPA++：首先将DA问题建模为图原语，设计新型谱正则化实现源-目标域图在特征空间中的对齐；其次引入细粒度邻域感知传播机制，增强目标域的判别性；最后结合数据增强与一致性正则化，使SPA++能适配多种典型及挑战性分布场景。理论分析方面，提供了基于图的域自适应泛化界，阐明谱对齐与平滑一致性的关键作用。大量基准测试表明，SPA++持续优于现有先进方法，在多种挑战性场景下均展现出更强鲁棒性与适应性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。