arXiv：cs.LG（机器学习，全量分类）· Zekai Chen, Jiayang Xing, Xun Wu, Miao Zhang, Xunkai Li, Kairui Yang, Zhengyu Wu, Xu Wang, Rong-Hua Li, Guoren Wang·· 14 小时前AI 评分31
MOVE：面向图学习的多模态开放世界验证与扩展框架
MOVE: Multimodal Open-world Verification and Expansion for Graph Learning
AI 导读
针对多模态图学习中部署后新类别出现、而模型标签空间固定的问题，研究者提出 MOVE 框架，联合视觉 token、文本属性与图上下文识别无法归入现有类别的节点，并用多模态 LLM 生成候选类别，仅在多模态证据一致支持时才扩展类别空间。实验显示，MOVE 在未知节点识别、开放域标注和下游图学习任务上平均提升 11.87%。
正文
Abstract:Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, while models are trained with a fixed label space. Existing approaches typically detect unknown nodes and use LLMs to generate candidate class descriptions, but they do not determine whether existing classes are insufficient to cover these nodes or whether a generated class is reliable enough to expand the class space. Our empirical study reveals three challenges: multimodal information beyond individual modalities is required for unknown-node identification, LLM-generated class descriptions may not fully capture multimodal class characteristics, and directly adding candidate classes can introduce redundant categories. Based on these observations, we propose MOVE, a multimodal open-world class verification and expansion framework. MOVE identifies nodes that cannot be assigned to existing classes by jointly considering visual tokens, textual attributes, and graph context, leverages a multimodal LLM to generate candidate classes, and selectively expands the class space only when candidates are consistently supported by multimodal evidence without introducing unnecessary categories. Experiments demonstrate that MOVE achieves an average improvement of 11.87\% across unknown recognition, open-domain annotation, and downstream graph learning tasks.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00268 [cs.LG] |
| (or arXiv:2610.00268v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00268 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zekai Chen [view email]
[v1]
Thu, 24 Sep 2026 10:42:42 UTC (2,484 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org