Scaling Graph Similarity Learning with Graph Neural Networks
The paper addresses graph similarity computation, where exact Graph Edit Distance and Maximum Common Subgraph are NP-hard, and existing GNN approaches have mainly been tested on small graphs. It proposes FiLSim, a scalable GNN-based framework, and a sequential graph-editing strategy for constructing large-scale datasets with reliable GED labels. FiLSim is evaluated on four standard benchmarks and four newly created large-scale datasets, remaining accurate on graphs with more than 150,000 nodes where baselines run out of memory or fail to learn. It can score all test pairs within seconds on a single GPU.
It introduces a scalable GNN framework and large-scale labeled datasets for a computationally hard graph-learning task, offering useful evidence for researchers working on graph similarity at scale.
Comments & Questions (0)
No comments yet
Be the first to comment!