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)

Paper ID: 14419
Venue: VLDB
Year: 2025
Pagerank: 5.2528121e-05
Overall Rank: 9,554 | 34.46%
DOI: 10.14778/3712221.3712237

Incoming Non-self Citations Over Time

Authors

1. Wenfei Fan (Beihang University; Shenzhen University; University of Edinburgh)
2. Lihang Fan (Beihang University)
3. Dandan Lin (Shenzhen University)
4. Min Xie (Shenzhen University)

BibTeX Citation

@article{fan_vldb25,
        title = {{Explaining GNN-based Recommendations in Logic}},
        author = {Fan, Wenfei and Fan, Lihang and Lin, Dandan and Xie, Min},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {3},
        pages = {715--728},
        doi = {10.14778/3712221.3712237},
        url = {https://doi.org/10.14778/3712221.3712237},
        year = {2025}
}

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 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
1,411	word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data	2020	PODS	0.00010852334
1,951	Interpretable Data-Based Explanations for Fairness Debugging	2022	SIGMOD	9.4252389e-05
2,324	Dependencies for Graphs	2017	PODS	8.7506505e-05
2,973	Functional Dependencies for Graphs	2016	SIGMOD	7.9083516e-05
4,832	Association Rules with Graph Patterns	2015	VLDB	6.4877e-05
6,354	On Data-Aware Global Explainability of Graph Neural Networks	2023	VLDB	5.9027055e-05
8,095	Towards Event Prediction in Temporal Graphs	2022	VLDB	5.4877864e-05
8,113	Capturing Associations in Graphs	2020	VLDB	5.484341e-05
9,627	Making It Tractable to Catch Duplicates and Conflicts in Graphs	2023	SIGMOD	5.2434488e-05
11,410	Enriching Recommendation Models with Logic Conditions	2023	SIGMOD	5.093636e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	2,688	Accelerating Recommendation System Training by Leveraging Popular Choices	2022	VLDB
2	10,557	Database Views as Explanations for Relational Deep Learning	2026	VLDB
3	3,048	FlexRecs: Expressing and Combining Flexible Recommendations	2009	SIGMOD
4	4,736	REX: Explaining Relationships between Entity Pairs	2012	VLDB
5	11,451	HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks	2023	VLDB
6	6,295	Explaining Link Prediction Systems based on Knowledge Graph Embeddings	2022	SIGMOD
7	10,943	Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation	2025	VLDB
8	6,354	On Data-Aware Global Explainability of Graph Neural Networks	2023	VLDB
9	11,410	Enriching Recommendation Models with Logic Conditions	2023	SIGMOD
10	9,922	View-based Explanations for Graph Neural Networks	2024	SIGMOD