LocalGCL: Local-aware Contrastive Learning for Graphs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916141014712320 |
|---|---|
| author | Jiang, Haojun Sun, Jiawei Li, Jie Wu, Chentao |
| author_facet | Jiang, Haojun Sun, Jiawei Li, Jie Wu, Chentao |
| contents | Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually prompts the growth of self-supervised learning (SSL) techniques. As a dominant approach of SSL, Contrastive learning (CL) learns discriminative representations by differentiating between positive and negative samples. However, when applied to graph data, it overemphasizes global patterns while neglecting local structures. To tackle the above issue, we propose \underline{Local}-aware \underline{G}raph \underline{C}ontrastive \underline{L}earning (\textbf{\methnametrim}), a self-supervised learning framework that supplementarily captures local graph information with masking-based modeling compared with vanilla contrastive learning. Extensive experiments validate the superiority of \methname against state-of-the-art methods, demonstrating its promise as a comprehensive graph representation learner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17345 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LocalGCL: Local-aware Contrastive Learning for Graphs Jiang, Haojun Sun, Jiawei Li, Jie Wu, Chentao Machine Learning Artificial Intelligence Graph representation learning (GRL) makes considerable progress recently, which encodes graphs with topological structures into low-dimensional embeddings. Meanwhile, the time-consuming and costly process of annotating graph labels manually prompts the growth of self-supervised learning (SSL) techniques. As a dominant approach of SSL, Contrastive learning (CL) learns discriminative representations by differentiating between positive and negative samples. However, when applied to graph data, it overemphasizes global patterns while neglecting local structures. To tackle the above issue, we propose \underline{Local}-aware \underline{G}raph \underline{C}ontrastive \underline{L}earning (\textbf{\methnametrim}), a self-supervised learning framework that supplementarily captures local graph information with masking-based modeling compared with vanilla contrastive learning. Extensive experiments validate the superiority of \methname against state-of-the-art methods, demonstrating its promise as a comprehensive graph representation learner. |
| title | LocalGCL: Local-aware Contrastive Learning for Graphs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.17345 |