Scalable GNN Explanations with Distributed Shapley Values

Summary: DistShap distributes Shapley-based GNN explanations across GPUs, parallelizing subgraph sampling, inference, and least-squares attribution. It achieves strong accuracy while scaling explanations to million-edge GNNs on 128 GPUs. (summarized by gpt-5.6-luna on Jul 09 2026)

Paper ID: 14314
Venue: VLDB
Year: 2026
Pagerank: -
Overall Rank: 13,102 | 8.94%
DOI: 10.14778/3811243.3811247

Incoming Non-self Citations Over Time

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

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
9,766	View-based Explanations for Graph Neural Networks	2024	SIGMOD	4.2815042e-05
10,798	Graph Compression for Interpretable Graph Neural Network Inference At Scale	2025	VLDB	4.1905499e-05
9,095	Scapin: Scalable Graph Structure Perturbation by Augmented Influence Maximization	2023	SIGMOD	4.3925641e-05
8,459	D3-GNN: Dynamic Distributed Dataflow for Streaming Graph Neural Networks	2024	VLDB	4.5008938e-05
2,399	ByteGNN: Efficient Graph Neural Network Training at Large Scale	2022	VLDB	8.8869693e-05
5,431	SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization	2022	VLDB	5.5104776e-05
10,664	Effective and Efficient Distributed Temporal Graph Learning through Hotspot Memory Sharing	2025	VLDB	4.1905499e-05
9,596	Scalable Graph Convolutional Network Training on Distributed-Memory Systems	2023	VLDB	4.3150788e-05
6,156	On Data-Aware Global Explainability of Graph Neural Networks	2023	VLDB	5.1779507e-05
3,092	Scalable and Efficient Full-Graph GNN Training for Large Graphs	2023	SIGMOD	7.5869574e-05