Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917080393056256 |
|---|---|
| author | Chen, Zhuomin Ni, Jingchao Salehi, Hojat Allah Zheng, Xu Schafir, Esteban Shirani, Farhad Luo, Dongsheng |
| author_facet | Chen, Zhuomin Ni, Jingchao Salehi, Hojat Allah Zheng, Xu Schafir, Esteban Shirani, Farhad Luo, Dongsheng |
| contents | Self-supervised graph representation learning (GRL) typically generates paired graph augmentations from each graph to infer similar representations for augmentations of the same graph, but distinguishable representations for different graphs. While effective augmentation requires both semantics-preservation and data-perturbation, most existing GRL methods focus solely on data-perturbation, leading to suboptimal solutions. To fill the gap, in this paper, we propose a novel method, Explanation-Preserving Augmentation (EPA), which leverages graph explanation for semantics-preservation. EPA first uses a small number of labels to train a graph explainer, which infers the subgraphs that explain the graph's label. Then these explanations are used for generating semantics-preserving augmentations for boosting self-supervised GRL. Thus, the entire process, namely EPA-GRL, is semi-supervised. We demonstrate theoretically, using an analytical example, and through extensive experiments on a variety of benchmark datasets, that EPA-GRL outperforms the state-of-the-art (SOTA) GRL methods that use semantics-agnostic augmentations. The code is available at https://github.com/realMoana/EPA-GRL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12657 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning Chen, Zhuomin Ni, Jingchao Salehi, Hojat Allah Zheng, Xu Schafir, Esteban Shirani, Farhad Luo, Dongsheng Machine Learning Self-supervised graph representation learning (GRL) typically generates paired graph augmentations from each graph to infer similar representations for augmentations of the same graph, but distinguishable representations for different graphs. While effective augmentation requires both semantics-preservation and data-perturbation, most existing GRL methods focus solely on data-perturbation, leading to suboptimal solutions. To fill the gap, in this paper, we propose a novel method, Explanation-Preserving Augmentation (EPA), which leverages graph explanation for semantics-preservation. EPA first uses a small number of labels to train a graph explainer, which infers the subgraphs that explain the graph's label. Then these explanations are used for generating semantics-preserving augmentations for boosting self-supervised GRL. Thus, the entire process, namely EPA-GRL, is semi-supervised. We demonstrate theoretically, using an analytical example, and through extensive experiments on a variety of benchmark datasets, that EPA-GRL outperforms the state-of-the-art (SOTA) GRL methods that use semantics-agnostic augmentations. The code is available at https://github.com/realMoana/EPA-GRL. |
| title | Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.12657 |