# Subgraph Neural Networks

arXiv: https://arxiv.org/abs/2006.10538 · HTML: https://mlsanity.com/paper/2006.10538/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 30 of 73)

- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks](https://mlsanity.com/paper/2103.03212/) (2021)
- [Structure-Aware Transformer for Graph Representation Learning](https://mlsanity.com/paper/2202.03036/) (2022)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [A Generalization of ViT/MLP-Mixer to Graphs](https://mlsanity.com/paper/2212.13350/) (2022)
- [Graph Representation Learning in Biomedicine](https://mlsanity.com/paper/2104.04883/) (2021)
- [SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism](https://mlsanity.com/paper/2101.08170/) (2021)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Multimodal learning with graphs](https://mlsanity.com/paper/2209.03299/) (2022)
- [Improving Subgraph Recognition with Variational Graph Information Bottleneck](https://mlsanity.com/paper/2112.09899/) (2021)
- [Property-Aware Relation Networks for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2107.07994/) (2021)
- [Autobahn: Automorphism-based Graph Neural Nets](https://mlsanity.com/paper/2103.01710/) (2021)
- [Recognizing Predictive Substructures with Subgraph Information Bottleneck](https://mlsanity.com/paper/2103.11155/) (2021)
- [Conditional Graph Information Bottleneck for Molecular Relational Learning](https://mlsanity.com/paper/2305.01520/) (2023)
- [Anomaly Detection in Dynamic Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2406.00134/) (2024)
- [RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search](https://mlsanity.com/paper/2206.06757/) (2022)
- [Beyond Message Passing: Neural Graph Pattern Machine](https://mlsanity.com/paper/2501.18739/) (2025)
- [Expressive Sign Equivariant Networks for Spectral Geometric Learning](https://mlsanity.com/paper/2312.02339/) (2023)
- [Neural Predicting Higher-order Patterns in Temporal Networks](https://mlsanity.com/paper/2106.06039/) (2021)
- [Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks](https://mlsanity.com/paper/2501.16944/) (2025)
- [GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning](https://mlsanity.com/paper/2511.05592/) (2025)
- [Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction](https://mlsanity.com/paper/2407.20871/) (2024)
- [Generic and Trend-aware Curriculum Learning for Relation Extraction in Graph Neural Networks](https://mlsanity.com/paper/2205.08625/) (2022)
- [Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data](https://mlsanity.com/paper/2202.00097/) (2022)
- [SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning](https://mlsanity.com/paper/2303.03379/) (2023)
- [The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset](https://mlsanity.com/paper/2404.19109/) (2024)
- [SHINE: SubHypergraph Inductive Neural nEtwork](https://mlsanity.com/paper/2210.07309/) (2022)
- [Simplifying Subgraph Representation Learning for Scalable Link Prediction](https://mlsanity.com/paper/2301.12562/) (2023)
- [A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizability](https://mlsanity.com/paper/2406.09031/) (2024)
- [State of the Art and Potentialities of Graph-level Learning](https://mlsanity.com/paper/2301.05860/) (2023)

## Abstract (arXiv)

Deep learning methods for graphs achieve remarkable performance on many node-level and graph-level prediction tasks. However, despite the proliferation of the methods and their success, prevailing Graph Neural Networks (GNNs) neglect subgraphs, rendering subgraph prediction tasks challenging to tackle in many impactful applications. Further, subgraph prediction tasks present several unique challenges: subgraphs can have non-trivial internal topology, but also carry a notion of position and external connectivity information relative to the underlying graph in which they exist. Here, we introduce SubGNN, a subgraph neural network to learn disentangled subgraph representations. We propose a novel subgraph routing mechanism that propagates neural messages between the subgraph's components and randomly sampled anchor patches from the underlying graph, yielding highly accurate subgraph representations. SubGNN specifies three channels, each designed to capture a distinct aspect of subgraph topology, and we provide empirical evidence that the channels encode their intended properties. We design a series of new synthetic and real-world subgraph datasets. Empirical results for subgraph classification on eight datasets show that SubGNN achieves considerable performance gains, outperforming strong baseline methods, including node-level and graph-level GNNs, by 19.8% over the strongest baseline. SubGNN performs exceptionally well on challenging biomedical datasets where subgraphs have complex topology and even comprise multiple disconnected components.