Pith. sign in

REVIEW 3 cited by

Neural Subgraph Matching

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.03092 v2 pith:54LN3ZAQ submitted 2020-07-06 cs.LG stat.ML

Rex (Zhitao) Ying , Zhaoyu Lou , Jiaxuan You , Chengtao Wen , Arquimedes Canedo , Jure Leskovec This is my paper · ORCID
classification cs.LGstat.ML
keywords matchingsubgraphneuromatchexistinggraphneuralproblemquery
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Subgraph matching is the problem of determining the presence and location(s) of a given query graph in a large target graph. Despite being an NP-complete problem, the subgraph matching problem is crucial in domains ranging from network science and database systems to biochemistry and cognitive science. However, existing techniques based on combinatorial matching and integer programming cannot handle matching problems with both large target and query graphs. Here we propose NeuroMatch, an accurate, efficient, and robust neural approach to subgraph matching. NeuroMatch decomposes query and target graphs into small subgraphs and embeds them using graph neural networks. Trained to capture geometric constraints corresponding to subgraph relations, NeuroMatch then efficiently performs subgraph matching directly in the embedding space. Experiments demonstrate NeuroMatch is 100x faster than existing combinatorial approaches and 18% more accurate than existing approximate subgraph matching methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval

    cs.CV 2025-05 conditional novelty 6.0 of 10

    SCENIR, an unsupervised graph autoencoder, ranks images by scene graph similarity and outperforms supervised caption-trained GNNs on a Graph Edit Distance benchmark.

  2. NGM-RAG: Neural Graph Matching based Retrieval-Augmented Generation

    cs.IR 2026-07 conditional novelty 5.0 of 10

    Combining Levenshtein, BM25, and GNN node matching with adaptive weights yields higher EM/F1 and win rates than NaiveRAG, GraphRAG, and LightRAG on multi-hop QA and long-context tasks.

  3. Target Circuit Matching in Large-Scale Netlists using GNN-Based Region Prediction

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A GNN-based region ranking plus VF2 verification matches all target circuits in large netlists with lower runtime than VF2 and neural baselines.

Pith tools