analiza aiqbench
This paper introduces EviGDA, a novel framework for graph domain adaptation that combines a graph-aware expert with a graph-free local expert to capture complementary predictive evidence under structural shifts. By optimizing these experts independently and merging them only at inference, the method avoids complex joint training while outperforming existing state-of-the-art baselines across multiple datasets. The work advances machine learning by addressing limitations in current representation-based approaches for transfer learning on graphs.
Graph Domain Adaptation Does Not End with Representation Learning
arXiv:2609.25692v1 Announce Type: new 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.
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.
Machine Learning (cs.LG)
arXiv:2609.25692 [cs.LG]
(or arXiv:2609.25692v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.25692 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 273 cuvinte
Subiecte conexe
Cross-Resolution Semantic Learning for Graph Domain Adaptation
arXiv · 3 aug. 2026
HYDRA: Proactive Android Malware Drift Adaptation via Hierarchical Graph Contrastive Learning
arXiv · 23 sept. 2026
MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
arXiv · 26 aug. 2026
Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection
arXiv · 21 aug. 2026