LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917809140793344 |
|---|---|
| author | Lin, Tianqianjin Yan, Pengwei Song, Kaisong Jiang, Zhuoren Kang, Yangyang Lin, Jun Yuan, Weikang Cao, Junjie Sun, Changlong Liu, Xiaozhong |
| author_facet | Lin, Tianqianjin Yan, Pengwei Song, Kaisong Jiang, Zhuoren Kang, Yangyang Lin, Jun Yuan, Weikang Cao, Junjie Sun, Changlong Liu, Xiaozhong |
| contents | Graph foundation models (GFMs) have recently gained significant attention. However, the unique data processing and evaluation setups employed by different studies hinder a deeper understanding of their progress. Additionally, current research tends to focus on specific subsets of graph learning tasks, such as structural tasks, node-level tasks, or classification tasks. As a result, they often incorporate specialized modules tailored to particular task types, losing their applicability to other graph learning tasks and contradicting the original intent of foundation models to be universal. Therefore, to enhance consistency, coverage, and diversity across domains, tasks, and research interests within the graph learning community in the evaluation of GFMs, we propose GFMBench-a systematic and comprehensive benchmark comprising 26 datasets. Moreover, we introduce LangGFM, a novel GFM that relies entirely on large language models. By revisiting and exploring the effective graph textualization principles, as well as repurposing successful techniques from graph augmentation and graph self-supervised learning within the language space, LangGFM achieves performance on par with or exceeding the state of the art across GFMBench, which can offer us new perspectives, experiences, and baselines to drive forward the evolution of GFMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_14961 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model Lin, Tianqianjin Yan, Pengwei Song, Kaisong Jiang, Zhuoren Kang, Yangyang Lin, Jun Yuan, Weikang Cao, Junjie Sun, Changlong Liu, Xiaozhong Machine Learning Artificial Intelligence Social and Information Networks Graph foundation models (GFMs) have recently gained significant attention. However, the unique data processing and evaluation setups employed by different studies hinder a deeper understanding of their progress. Additionally, current research tends to focus on specific subsets of graph learning tasks, such as structural tasks, node-level tasks, or classification tasks. As a result, they often incorporate specialized modules tailored to particular task types, losing their applicability to other graph learning tasks and contradicting the original intent of foundation models to be universal. Therefore, to enhance consistency, coverage, and diversity across domains, tasks, and research interests within the graph learning community in the evaluation of GFMs, we propose GFMBench-a systematic and comprehensive benchmark comprising 26 datasets. Moreover, we introduce LangGFM, a novel GFM that relies entirely on large language models. By revisiting and exploring the effective graph textualization principles, as well as repurposing successful techniques from graph augmentation and graph self-supervised learning within the language space, LangGFM achieves performance on par with or exceeding the state of the art across GFMBench, which can offer us new perspectives, experiences, and baselines to drive forward the evolution of GFMs. |
| title | LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model |
| topic | Machine Learning Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2410.14961 |