# Charting the Design Space of Neural Graph Representations for Subgraph Matching

Source: [Charting the Design Space of Neural Graph Representations for Subgraph Matching](<https://www.sota2.com/research/paper/69004e063ef7ccd74e5e2c1d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-29T05:04:11.035Z

Authors: Vaibhav Raj, Indradyumna Roy, Ashwin Ramachandran, Soumen Chakrabarti, Abir De

Published: 2025-10-27T00:58:29.000Z

## Abstract

Subgraph matching is vital in knowledge graph (KG) question answering, molecule design, scene graph, code and circuit search, etc. Neural methods have shown promising results for subgraph matching. Our study of recent systems suggests refactoring them into a unified design space for graph matching networks. Existing methods occupy only a few isolated patches in this space, which remains largely uncharted. We undertake the first comprehensive exploration of this space, featuring such axes as attention-based vs. soft permutation-based interaction between query and corpus graphs, aligning nodes vs. edges, and the form of the final scoring network that integrates neural representations of the graphs. Our extensive experiments reveal that judicious and hitherto-unexplored combinations of choices in this space lead to large performance benefits. Beyond better performance, our study uncovers valuable insights and establishes general design principles for neural graph representation and interaction, which may be of wider interest.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.22897>)

[PDF](<https://arxiv.org/pdf/2510.22897.pdf>)
