HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks
Summary: HENCE-X: a heterogeneity-agnostic, causality-guided explainer for deep graph networks producing joint feature- and topology-level factual and counterfactual explanations. Theoretically guaranteed to recover the prediction's Markov blanket and empirically outperforms SOTA on real datasets. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Ge Lv
- 2. Chen Jason Zhang
- 3. Lei Chen
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,233 | Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling | 2026 | VLDB | 5.1725247e-05 |
Previous
Page 1 / 1
Next
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 |
|---|---|---|---|---|
| 4,606 | xFraud: Explainable Fraud Transaction Detection | 2022 | VLDB | 6.6790008e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| Overall Rank | Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,798 | Graph Compression for Interpretable Graph Neural Network Inference At Scale | 2025 | VLDB | 5.1725247e-05 |
| 2,950 | Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals | 2021 | SIGMOD | 7.9798509e-05 |
| 10,862 | MSGNN: Masked Schema based Graph Neural Networks | 2025 | VLDB | 5.1725247e-05 |
| 10,438 | CausalExplain: Causal Explanations of Black-box Models with Training Data Subsets | 2025 | SIGMOD | 5.1725247e-05 |
| 4,606 | xFraud: Explainable Fraud Transaction Detection | 2022 | VLDB | 6.6790008e-05 |
| 9,401 | Explaining GNN-based Recommendations in Logic | 2025 | VLDB | 5.3341661e-05 |
| 4,736 | XInsight: eXplainable Data Analysis Through The Lens of Causality | 2023 | SIGMOD | 6.6012363e-05 |
| 10,269 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB | 5.1725247e-05 |
| 9,757 | View-based Explanations for Graph Neural Networks | 2024 | SIGMOD | 5.2759752e-05 |
| 6,274 | On Data-Aware Global Explainability of Graph Neural Networks | 2023 | VLDB | 5.9941248e-05 |