EUVIMEDEUVIMED entdecken
Crossref

Transferable Graph Condensation from the Causal Perspective

Huaming Du, Yijie Huang, Su Yao, Yiying Wang, Yueyang Zhou, Jingwen Yang, Jinshi Zhang, Han Ji, Yu Zhao, Guisong Liu, Hegui Zhang, Carl Yang und 1 weitere

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (17) · 14684-14692

DOI: 10.1609/aaai.v40i17.38487 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Huaming Du und 12 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing scale of graph datasets has significantly improved the performance of graph representation learning methods, but it has also introduced substantial training challenges. Graph dataset condensation techniques have emerged to compress large datasets into smaller yet information-rich datasets, while maintaining similar test performance. However, these methods strictly require downstream applications to match the original dataset and task, which often fails in cross-task and cross-domain scenarios. To address these challenges, we propose a novel causal-invariance-based and transferable graph dataset condensation method, named TGCC, providing effective and transferable condensed datasets. Specifically, to preserve domain-invariant knowledge, we first extract domain causal-invariant features from the spatial domain of the graph using causal interventions. Then, to fully capture the structural and feature information of the original graph, we perform enhanced condensation operations. Finally, through spectral-domain Enhanced contrastive learning, we inject the causal-invariant features into the condensed graph, ensuring that the compressed graph retains the causal information of the original graph. Experimental results on five public datasets and our novel FinReport dataset demonstrate that TGCC achieves up to a 13.41% improvement in cross-task and cross-domain complex scenarios compared to existing methods, and achieves state-of-the-art performance on 5 out of 6 datasets in the single dataset and task scenario.

Zitieren

APA

Du, H., Huang, Y., Yao, S., Wang, Y., Zhou, Y., Yang, J., Zhang, J., Ji, H., Zhao, Y., Liu, G., Zhang, H., Yang, C., & Kou, G. (2026). Transferable Graph Condensation from the Causal Perspective. Proceedings of the AAAI Conference on Artificial Intelligence, 40(17), 14684-14692. https://doi.org/10.1609/aaai.v40i17.38487

Vancouver

Du H, Huang Y, Yao S, Wang Y, Zhou Y, Yang J, et al. Transferable Graph Condensation from the Causal Perspective. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(17):14684-14692. doi:10.1609/aaai.v40i17.38487

BibTeX
@article{Du2026,
  author = {Du, Huaming and Huang, Yijie and Yao, Su and Wang, Yiying and Zhou, Yueyang and Yang, Jingwen and Zhang, Jinshi and Ji, Han and Zhao, Yu and Liu, Guisong and Zhang, Hegui and Yang, Carl and Kou, Gang},
  title = {Transferable Graph Condensation from the Causal Perspective},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {17},
  pages = {14684--14692},
  doi = {10.1609/aaai.v40i17.38487}
}
Kostenlos starten →