GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights
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_ | 1866918191208333312 |
|---|---|
| author | Gong, Shengbo Ni, Juntong Sachdeva, Noveen Yang, Carl Jin, Wei |
| author_facet | Gong, Shengbo Ni, Juntong Sachdeva, Noveen Yang, Carl Jin, Wei |
| contents | Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. This condensed graph has shown promise in accelerating graph neural networks while preserving performance comparable to those achieved with the original, larger graphs. Additionally, this technique facilitates downstream applications like neural architecture search and deepens our understanding of redundancies in large graphs. Despite the rapid development of GC methods, particularly for node classification, a unified evaluation framework is still lacking to systematically compare different GC methods or clarify key design choices for improving their effectiveness. To bridge these gaps, we introduce \textbf{GC4NC}, a comprehensive framework for evaluating diverse GC methods on node classification across multiple dimensions including performance, efficiency, privacy preservation, denoising ability, NAS effectiveness, and transferability. Our systematic evaluation offers novel insights into how condensed graphs behave and the critical design choices that drive their success. These findings pave the way for future advancements in GC methods, enhancing both performance and expanding their real-world applications. Our code is available at https://github.com/Emory-Melody/GraphSlim/tree/main/benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16715 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights Gong, Shengbo Ni, Juntong Sachdeva, Noveen Yang, Carl Jin, Wei Machine Learning Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. This condensed graph has shown promise in accelerating graph neural networks while preserving performance comparable to those achieved with the original, larger graphs. Additionally, this technique facilitates downstream applications like neural architecture search and deepens our understanding of redundancies in large graphs. Despite the rapid development of GC methods, particularly for node classification, a unified evaluation framework is still lacking to systematically compare different GC methods or clarify key design choices for improving their effectiveness. To bridge these gaps, we introduce \textbf{GC4NC}, a comprehensive framework for evaluating diverse GC methods on node classification across multiple dimensions including performance, efficiency, privacy preservation, denoising ability, NAS effectiveness, and transferability. Our systematic evaluation offers novel insights into how condensed graphs behave and the critical design choices that drive their success. These findings pave the way for future advancements in GC methods, enhancing both performance and expanding their real-world applications. Our code is available at https://github.com/Emory-Melody/GraphSlim/tree/main/benchmark. |
| title | GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.16715 |