Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914872310104064 |
|---|---|
| author | Huang, Zhenhua Li, Kunhao Wang, Shaojie Jia, Zhaohong Zhu, Wentao Mehrotra, Sharad |
| author_facet | Huang, Zhenhua Li, Kunhao Wang, Shaojie Jia, Zhaohong Zhu, Wentao Mehrotra, Sharad |
| contents | Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node and graph representations. To address this limitation, we propose a novel Graph structure Prompt Learning method (GPL) to enhance the training of GNNs, which is inspired by prompt mechanisms in natural language processing. GPL employs task-independent graph structure losses to encourage GNNs to learn intrinsic graph characteristics while simultaneously solving downstream tasks, producing higher-quality node and graph representations. In extensive experiments on eleven real-world datasets, after being trained by GPL, GNNs significantly outperform their original performance on node classification, graph classification, and edge prediction tasks (up to 10.28%, 16.5%, and 24.15%, respectively). By allowing GNNs to capture the inherent structural prompts of graphs in GPL, they can alleviate the issue of over-smooth and achieve new state-of-the-art performances, which introduces a novel and effective direction for GNN research with potential applications in various domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11361 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks Huang, Zhenhua Li, Kunhao Wang, Shaojie Jia, Zhaohong Zhu, Wentao Mehrotra, Sharad Machine Learning Social and Information Networks Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node and graph representations. To address this limitation, we propose a novel Graph structure Prompt Learning method (GPL) to enhance the training of GNNs, which is inspired by prompt mechanisms in natural language processing. GPL employs task-independent graph structure losses to encourage GNNs to learn intrinsic graph characteristics while simultaneously solving downstream tasks, producing higher-quality node and graph representations. In extensive experiments on eleven real-world datasets, after being trained by GPL, GNNs significantly outperform their original performance on node classification, graph classification, and edge prediction tasks (up to 10.28%, 16.5%, and 24.15%, respectively). By allowing GNNs to capture the inherent structural prompts of graphs in GPL, they can alleviate the issue of over-smooth and achieve new state-of-the-art performances, which introduces a novel and effective direction for GNN research with potential applications in various domains. |
| title | Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2407.11361 |