Explaining GNN-based Recommendations in Logic
Summary: Introduce Makex, a logic-based explanation framework that discovers Rules for ExPlanations (REPs)—a graph pattern Q plus precondition predicates X→M(x,y)—to expose topology and feature dependencies driving GNN recommender outputs. Defines REPs via 1-WL, gives algorithms for global REP discovery and top-k local explanations, and reports superior fidelity, sparsity, and efficiency versus prior methods. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Wenfei Fan
- 2. Lihang Fan
- 3. Dandan Lin
- 4. Min Xie
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 | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,190 | word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data | 2020 | PODS | 0.00013438056 |
| 1,867 | Interpretable Data-Based Explanations for Fairness Debugging | 2022 | SIGMOD | 0.00010272055 |
| 2,450 | Functional Dependencies for Graphs | 2016 | SIGMOD | 8.7882979e-05 |
| 2,527 | Dependencies for Graphs | 2017 | PODS | 8.5954406e-05 |
| 4,205 | Association Rules with Graph Patterns | 2015 | VLDB | 6.3597474e-05 |
| 6,153 | On Data-Aware Global Explainability of Graph Neural Networks | 2023 | VLDB | 5.1829258e-05 |
| 8,133 | Towards Event Prediction in Temporal Graphs | 2022 | VLDB | 4.5784634e-05 |
| 8,211 | Capturing Associations in Graphs | 2020 | VLDB | 4.5581054e-05 |
| 9,487 | Making It Tractable to Catch Duplicates and Conflicts in Graphs | 2023 | SIGMOD | 4.3341665e-05 |
| 11,209 | Enriching Recommendation Models with Logic Conditions | 2023 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next