Multiplex Graph Contrastive Learning with Soft Negatives
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929498855833600 |
|---|---|
| author | Zhao, Zhenhao Zhu, Minhong Wang, Chen Wang, Sijia Zhang, Jiqiang Chen, Li Cai, Weiran |
| author_facet | Zhao, Zhenhao Zhu, Minhong Wang, Chen Wang, Sijia Zhang, Jiqiang Chen, Li Cai, Weiran |
| contents | Graph Contrastive Learning (GCL) seeks to learn nodal or graph representations that contain maximal consistent information from graph-structured data. While node-level contrasting modes are dominating, some efforts commence to explore consistency across different scales. Yet, they tend to lose consistent information and be contaminated by disturbing features. Here, we introduce MUX-GCL, a novel cross-scale contrastive learning paradigm that utilizes multiplex representations as effective patches. While this learning mode minimizes contaminating noises, a commensurate contrasting strategy using positional affinities further avoids information loss by correcting false negative pairs across scales. Extensive downstream experiments demonstrate that MUX-GCL yields multiple state-of-the-art results on public datasets. Our theoretical analysis further guarantees the new objective function as a stricter lower bound of mutual information of raw input features and output embeddings, which rationalizes this paradigm. Code is available at https://github.com/MUX-GCL/Code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08010 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multiplex Graph Contrastive Learning with Soft Negatives Zhao, Zhenhao Zhu, Minhong Wang, Chen Wang, Sijia Zhang, Jiqiang Chen, Li Cai, Weiran Machine Learning Graph Contrastive Learning (GCL) seeks to learn nodal or graph representations that contain maximal consistent information from graph-structured data. While node-level contrasting modes are dominating, some efforts commence to explore consistency across different scales. Yet, they tend to lose consistent information and be contaminated by disturbing features. Here, we introduce MUX-GCL, a novel cross-scale contrastive learning paradigm that utilizes multiplex representations as effective patches. While this learning mode minimizes contaminating noises, a commensurate contrasting strategy using positional affinities further avoids information loss by correcting false negative pairs across scales. Extensive downstream experiments demonstrate that MUX-GCL yields multiple state-of-the-art results on public datasets. Our theoretical analysis further guarantees the new objective function as a stricter lower bound of mutual information of raw input features and output embeddings, which rationalizes this paradigm. Code is available at https://github.com/MUX-GCL/Code. |
| title | Multiplex Graph Contrastive Learning with Soft Negatives |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.08010 |