EviGDA is proposed, an Evidence-Augmented Graph Domain Adaptation framework that complements graph representation adaptation with a graph-free local expert, and shows that EviGDA outperforms state-of-the-art baselines.
Abstract
Graph domain adaptation (GDA) transfers knowledge from a labeled source graph to an unlabeled target graph under shifts in both node attributes and graph structure. Existing methods primarily adapt graph representations through propagation redesign, distribution alignment, or source-to-target transition modeling, but still rely on a single graph-propagating path for target prediction. This leaves open whether an adapted graph representation exhausts the predictive evidence available in the target domain, since the graph-aware expert and graph-free local expert may exhibit different failure modes under topological shifts. To address this limitation, we propose EviGDA, an Evidence-Augmented Graph Domain Adaptation framework that complements graph representation adaptation with a graph-free local expert. The graph-aware expert performs message passing and entropy-aware marginal alignment, while the graph-free local expert learns solely from source node features and labels without graph propagation or target alignment. The two experts are optimized independently and combined only at inference through a task-level constant probability mixture, preserving complementary evidence without joint training, learned routing, or target pseudo-labels. Extensive experiments on ten datasets and 16 transfer tasks show that EviGDA outperforms state-of-the-art baselines. Complementary prediction paths add value beyond graph representation alignment.
Attributed graph clustering aims to discover node groups by jointly exploiting node attributes and graph topology, yet its unsupervised nature makes model selection and adaptation inherently difficult. Existing methods typically train and tune a separate model for each input graph, leading to costly and fragile pipelin...
Yunhui Liu, Xu-Dong Jin, Kang Zhang et al.· 2 citations
This work introduces structure-aware entropy-based matching discrepancy, which jointly models feature uncertainty and structural coherence to ensure accurate feature adaptation between graphs and develops a domain-aware semi-hard negative sampling strategy that constructs informative contrastive sets by filtering unrel...
Ming-Can Wang, Jun-Chang Xin, Zhong-Ming Yao et al.· arXiv.org· 0 citations
DEAG is proposed, a reliability-aware prototype learning framework for data-efficient agentic GDA that estimates class reliability from retained source support and embedding compactness, and constructs stable reusable source anchors by blending empirical prototypes with classifier directions.
Multimodal graph learning has recently emerged as an effective paradigm for in corporating inter-entity relationships into multimodal representations. Existing studies have made substantial progress on how to construct and optimize graphs, but rarely consider a more fundamental question: whether additional relational s...
Ze-Kai Chen, Kai Hu, Yu-Xin Zeng et al.· 0 citations
GTAP (Graph Topology-Aware Pre-training), a self-supervised initialization framework for within-dataset graph classification, improves over a matched GCN trained from scratch and achieves competitive accuracy against published baselines on most datasets with available results.
A Hypergraph-enhanced graph contrastive learning framework for Graph Out-Of-Distribution detection (termed HGOOD), which constructs two branches to hierarchically mine graph compact semantics in a comprehensive manner and introduces a cross-branch prototype contrast that aligns the captured graph patterns with their cr...
Xuan-Ting Fan, Chen-Yu Wang, Yue-Yue Gao et al.· Proceedings of the Thirty-Fi...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026