Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912422361563136 |
|---|---|
| author | Fu, Xingbo Wang, Zehong Chen, Zihan Li, Jiazheng Zhu, Yaochen Lei, Zhenyu Shen, Cong Ye, Yanfang Zhang, Chuxu Li, Jundong |
| author_facet | Fu, Xingbo Wang, Zehong Chen, Zihan Li, Jiazheng Zhu, Yaochen Lei, Zhenyu Shen, Cong Ye, Yanfang Zhang, Chuxu Li, Jundong |
| contents | Graph learning models have demonstrated great prowess in learning expressive representations from large-scale graph data in a wide variety of real-world scenarios. As a prevalent strategy for training powerful graph learning models, the "pre-training, adaptation" scheme first pre-trains graph learning models on unlabeled graph data in a self-supervised manner and then adapts them to specific downstream tasks. During the adaptation phase, graph prompting emerges as a promising approach that learns trainable prompts while keeping the pre-trained graph learning models unchanged. In this paper, we present a systematic review of recent advancements in graph prompting. First, we introduce representative graph pre-training methods that serve as the foundation step of graph prompting. Next, we review mainstream techniques in graph prompting and elaborate on how they design learnable prompts for graph prompting. Furthermore, we summarize the real-world applications of graph prompting from different domains. Finally, we discuss several open challenges in existing studies with promising future directions in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08326 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Prompting for Graph Learning Models: Recent Advances and Future Directions Fu, Xingbo Wang, Zehong Chen, Zihan Li, Jiazheng Zhu, Yaochen Lei, Zhenyu Shen, Cong Ye, Yanfang Zhang, Chuxu Li, Jundong Machine Learning Artificial Intelligence Graph learning models have demonstrated great prowess in learning expressive representations from large-scale graph data in a wide variety of real-world scenarios. As a prevalent strategy for training powerful graph learning models, the "pre-training, adaptation" scheme first pre-trains graph learning models on unlabeled graph data in a self-supervised manner and then adapts them to specific downstream tasks. During the adaptation phase, graph prompting emerges as a promising approach that learns trainable prompts while keeping the pre-trained graph learning models unchanged. In this paper, we present a systematic review of recent advancements in graph prompting. First, we introduce representative graph pre-training methods that serve as the foundation step of graph prompting. Next, we review mainstream techniques in graph prompting and elaborate on how they design learnable prompts for graph prompting. Furthermore, we summarize the real-world applications of graph prompting from different domains. Finally, we discuss several open challenges in existing studies with promising future directions in this field. |
| title | Graph Prompting for Graph Learning Models: Recent Advances and Future Directions |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.08326 |