DeSCo: Towards Generalizable and Scalable Deep Subgraph Counting

TL;DR

DeSCo is a scalable neural pipeline for deep subgraph counting that accurately predicts counts and positions on large graphs, outperforming existing methods with significant error reduction.

Contribution

DeSCo introduces a novel canonical partition and a subgraph-based GNN with gossip propagation for scalable, accurate subgraph counting.

Findings

Outperforms state-of-the-art neural methods by 137x in mean squared error.

Maintains polynomial runtime complexity.

Validated on eight diverse real-world datasets.

Abstract

We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training. Firstly, DeSCo uses a novel canonical partition and divides the large target graph into small neighborhood graphs, greatly reducing the count variation while guaranteeing no missing or double-counting. Secondly, neighborhood counting uses an expressive subgraph-based heterogeneous graph neural network to accurately count in each neighborhood. Finally, gossip propagation propagates neighborhood counts with learnable gates to harness the inductive biases of motif counts. DeSCo is evaluated on eight real-world datasets from various domains. It outperforms state-of-the-art neural methods with 137x improvement in the mean squared error of count prediction, while maintaining the polynomial runtime complexity. Our open source project is at https://github.com/fuvty/DeSCo.