Graph Compression for Interpretable Graph Neural Network Inference At Scale

We demonstrate ExGIS , a parallel inference query engine to support explainable Graph Neural Network (GNNs) inference analysis in large graphs. (1) For a class of GNNs

ℳ L

with at most L layers, and a graph G , ExGIS performs an offline, once-for-all compression of G to a small graph

G c

, such that for any inference query Q that requests the output of any GNN M ∈

ℳ L

on any node v in

G, G c

can be directly queried to yield correct output without decompression. (2) Given a workload W of inference queries that requests the output of GNNs from ℳ over G , ExGIS perform fast online GNN inference and interpretation in parallel. It dynamically partitions W to balance workloads, and (a) executes inference that only consults compressed graph

G c

without decompression, and (b) directly yields concise, explanatory subgraphs from

G c

that can clarify the query output with high fidelity, all in parallel. Moreover, ExGIS integrates visual, interactive interfaces for query performance analysis, and a Large Language Models (LLMs)- enabled interpreter to support user-friendly, natural language explanation of query outputs. We demonstrate the compression rate and scalability of ExGIS, and its application in interpretable anomaly detection over bitcoin transaction networks and academic networks.