发表机构
School of Computer Science and Engineering, Northeastern University; The Department of Computer Science, Aalborg University; School of Computing and Information Systems, Singapore Management University; College of Medicine and Biological Information Engineering, Northeastern University（东北大学计算机科学与工程学院; 奥尔堡大学计算机科学系; 新加坡管理大学计算与信息学院; 东北大学医学与生物信息工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图迁移学习中知识可靠性不均导致的负迁移和计算开销问题，提出选择性不确定性感知对比表示方法SUCRe，通过熵匹配差异和半硬负采样实现高效且准确的图知识迁移。
AI 中文摘要
图迁移学习（GTL）提供了一种有前景的范式，用于将带有充足标签的源图知识适应到标签稀缺的目标图。然而，现有方法通常假设迁移的知识是均匀可靠的，忽略了由跨图结构和分布偏移引起的样本可迁移性差异。这一局限性导致负迁移和不必要的计算开销。在这项工作中，我们提出了SUCRe，一种用于GTL的选择性不确定性感知对比表示方法。其关键思想是根据估计的可靠性选择性地适应和迁移图知识。具体来说，我们引入了基于结构感知的熵匹配差异，它联合建模特征不确定性和结构一致性，以确保图之间准确的特征适应。此外，我们开发了一种领域感知的半硬负样本采样策略，通过过滤不可靠的跨域关系来构建信息丰富的对比集，在减少计算冗余的同时增强表示判别力。在图迁移基准上的大量实验表明，SUCRe在提高效率的同时实现了有竞争力的性能。
英文摘要
Graph transfer learning (GTL) provides a promising paradigm for adapting knowledge from source graphs with sufficient labels to label-scarce target graphs. However, existing approaches often assume that transferred knowledge is uniformly reliable, ignoring the different transferability of samples caused by structural and distribution shifts across graphs. This limitation leads to negative transfer and unnecessary computational overhead. In this work, we propose SUCRe, a selective uncertainty-aware contrastive representation method for GTL. The key idea is to selectively adapt and transfer graph knowledge according to its estimated reliability. Specifically, we introduce structure-aware entropy-based matching discrepancy, which jointly models feature uncertainty and structural coherence to ensure accurate feature adaptation between graphs. Moreover, we develop a domain-aware semi-hard negative sampling strategy that constructs informative contrastive sets by filtering unreliable cross-domain relationships, reducing computational redundancy while enhancing representation discrimination. Extensive experiments on graph transfer benchmarks demonstrate that SUCRe achieves competitive performance with improved efficiency.
