arXiv Machine Learning
Graph Domain Adaptation Does Not End with Representation Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 15
Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype Learning
arXiv:2609.14045v1 Announce Type: new Abstract: Agentic learning systems are often required to adapt after deployment by observing new data and reusing prior knowledge under limited supervision or fe...
arXiv Machine Learning
Aug 3
Cross-Resolution Semantic Learning for Graph Domain Adaptation
arXiv:2607. 29365v1 Announce Type: new Abstract: Graph Domain Adaptation (GDA) transfers predictive knowledge from labeled source graphs to unlabeled target graphs under distribution shift.
arXiv Machine Learning
Aug 3
Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
arXiv:2607. 28980v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for enabling knowledge transfer across diverse domains.
arXiv AI
Jul 21
Selectivity Matters: Source Node Influence Pruning for Unsupervised Graph Domain Adaptation
arXiv:2607. 17668v1 Announce Type: cross Abstract: Unsupervised Graph Domain Adaptation (UGDA) aims to facilitate knowledge transfer from a labeled source graph to an unlabeled target graph by mitigating cross-domain distribution shifts.
arXiv Machine Learning
Jun 2
Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
arXiv:2606. 00808v1 Announce Type: new Abstract: Source-free graph domain adaptation (SF-GDA) aims to adapt source-trained graph models to unlabeled target graphs when source graphs are no longer accessible.
arXiv Machine Learning
Jul 14
Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment
arXiv:2607. 11374v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains.