HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks

Summary: HENCE-X provides heterogeneity-agnostic, end-to-end multi-level explanations for homogeneous and heterogeneous DGNs, jointly modeling topology and features. Its causality-guided conditional-probability framework provably recovers the prediction’s Markov blanket and yields faithful factual/counterfactual explanations. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 13327
Venue: VLDB
Year: 2023
Pagerank: 5.093636e-05
Overall Rank: 11,451 | 21.44%
DOI: 10.14778/3611479.3611503

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Ge Lv (Hong Kong University of Science and Technology)
2. Chen Jason Zhang (Hong Kong Polytechnic University)
3. Lei Chen (Hong Kong University of Science and Technology)

BibTeX Citation

@article{lv_vldb23,
        title = {{HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks}},
        author = {Lv, Ge and Zhang, Chen Jason and Chen, Lei},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {11},
        pages = {2990--3003},
        doi = {10.14778/3611479.3611503},
        url = {https://doi.org/10.14778/3611479.3611503},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,521	Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling	2026	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
4,666	xFraud: Explainable Fraud Transaction Detection	2022	VLDB	6.577136e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,021	Graph Compression for Interpretable Graph Neural Network Inference At Scale	2025	VLDB
2	3,000	Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals	2021	SIGMOD
3	11,082	MSGNN: Masked Schema based Graph Neural Networks	2025	VLDB
4	10,709	CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets	2025	SIGMOD
5	9,554	Explaining GNN-based Recommendations in Logic	2025	VLDB
6	4,666	xFraud: Explainable Fraud Transaction Detection	2022	VLDB
7	4,876	XInsight: eXplainable Data Analysis Through The Lens of Causality	2023	SIGMOD
8	10,557	Database Views as Explanations for Relational Deep Learning	2026	VLDB
9	9,922	View-based Explanations for Graph Neural Networks	2024	SIGMOD
10	6,354	On Data-Aware Global Explainability of Graph Neural Networks	2023	VLDB