Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.05962 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913228587532288 |
|---|---|
| author | Fang, Junfeng Li, Xinglin Sui, Yongduo Gao, Yuan Zhang, Guibin Wang, Kun Wang, Xiang He, Xiangnan |
| author_facet | Fang, Junfeng Li, Xinglin Sui, Yongduo Gao, Yuan Zhang, Guibin Wang, Kun Wang, Xiang He, Xiangnan |
| contents | Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05962 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EXGC: Bridging Efficiency and Explainability in Graph Condensation Fang, Junfeng Li, Xinglin Sui, Yongduo Gao, Yuan Zhang, Guibin Wang, Kun Wang, Xiang He, Xiangnan Machine Learning Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC. |
| title | EXGC: Bridging Efficiency and Explainability in Graph Condensation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.05962 |