{"ID":2857592,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09394","arxiv_id":"2510.09394","title":"Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph","abstract":"The ``pre-train, prompt\" paradigm, designed to bridge the gap between pre-training tasks and downstream objectives, has been extended from the NLP domain to the graph domain and has achieved remarkable progress. Current mainstream graph prompt-tuning methods modify input or output features using learnable prompt vectors. However, existing approaches are confined to single-granularity (e.g., node-level or subgraph-level) during prompt generation, overlooking the inherently multi-scale structural information in graph data, which limits the diversity of prompt semantics. To address this issue, we pioneer the integration of multi-scale information into graph prompt and propose a Multi-Scale Graph Chain-of-Thought (MSGCOT) prompting framework. Specifically, we design a lightweight, low-rank coarsening network to efficiently capture multi-scale structural features as hierarchical basis vectors for prompt generation. Subsequently, mimicking human cognition from coarse-to-fine granularity, we dynamically integrate multi-scale information at each reasoning step, forming a progressive coarse-to-fine prompt chain. Extensive experiments on eight benchmark datasets demonstrate that MSGCOT outperforms the state-of-the-art single-granularity graph prompt-tuning method, particularly in few-shot scenarios, showcasing superior performance. The code is available at: https://github.com/zhengziyu77/MSGCOT.","short_abstract":"The ``pre-train, prompt\" paradigm, designed to bridge the gap between pre-training tasks and downstream objectives, has been extended from the NLP domain to the graph domain and has achieved remarkable progress. Current mainstream graph prompt-tuning methods modify input or output features using learnable prompt vector...","url_abs":"https://arxiv.org/abs/2510.09394","url_pdf":"https://arxiv.org/pdf/2510.09394v4","authors":"[\"Ziyu Zheng\",\"Yaming Yang\",\"Ziyu Guan\",\"Wei Zhao\",\"Xinyan Huang\",\"Weigang Lu\"]","published":"2025-10-10T13:48:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":608469,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2857592,"paper_url":"https://arxiv.org/abs/2510.09394","paper_title":"Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph","repo_url":"https://github.com/zhengziyu77/MSGCOT","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}