DBScholar

Back to papers

View-based Explanations for Graph Neural Networks

Summary: GVEX introduces Graph Views for GNN explanations, enabling class-specific, queryable insights. Two-tier views (patterns + induced subgraphs) with Sigma2P-hard optimization yield 1/2-approx explain-and-summarize and 1/4-approx single-pass incremental algorithms, scalable to real data. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
6911
Venue
SIGMOD
Year
2024
Pagerank
5.1955087e-05
Overall Rank
9,922 | 31.93%
DOI
10.1145/3639295

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{chen_sigmod24,
        title = {{View-based Explanations for Graph Neural Networks}},
        author = {Chen, Tingyang and Qiu, Dazhuo and Wu, Yinghui and Khan, Arijit and Ke, Xiangyu and Gao, Yunjun},
        series = {{SIGMOD} '24},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3639295},
        url = {https://dl.acm.org/doi/10.1145/3639295},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 8 of 8 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers