# subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs

arXiv: https://arxiv.org/abs/1606.08928 · HTML: https://mlsanity.com/paper/1606.08928/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2016.

## Built on by (most cited first, 19 of 19)

- [A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications](https://mlsanity.com/paper/2202.07893/) (2022)
- [Model-Agnostic Augmentation for Accurate Graph Classification](https://mlsanity.com/paper/2202.10107/) (2022)
- [WGCN: Graph Convolutional Networks with Weighted Structural Features](https://mlsanity.com/paper/2104.14060/) (2021)
- [Adaptive Visibility Graph Neural Network and its Application in Modulation Classification](https://mlsanity.com/paper/2106.08564/) (2021)
- [Motif-based Graph Representation Learning with Application to Chemical Molecules](https://mlsanity.com/paper/2208.04529/) (2022)
- [TSGN: Transaction Subgraph Networks for Identifying Ethereum Phishing Accounts](https://mlsanity.com/paper/2104.08767/) (2021)
- [State of the Art and Potentialities of Graph-level Learning](https://mlsanity.com/paper/2301.05860/) (2023)
- [Gradual Weisfeiler-Leman: Slow and Steady Wins the Race](https://mlsanity.com/paper/2209.09048/) (2022)
- [Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views](https://mlsanity.com/paper/2308.10077/) (2023)
- [Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting](https://mlsanity.com/paper/2211.15856/) (2022)
- [Network representation learning systematic review: ancestors and current development state](https://mlsanity.com/paper/2109.07583/) (2021)
- [Generalizing Weisfeiler-Lehman Kernels to Subgraphs](https://mlsanity.com/paper/2412.02181/) (2024)
- [Network Embedding Exploration Tool (NEExT)](https://mlsanity.com/paper/2503.15853/) (2025)
- [Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2104.06317/) (2021)
- [Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast](https://mlsanity.com/paper/2106.03723/) (2021)
- [A Prufer-Sequence Based Representation of Large Graphs for Structural Encoding of Logic Networks](https://mlsanity.com/paper/2209.01596/) (2022)
- [Multi-perspective Feedback-attention Coupling Model for Continuous-time Dynamic Graphs](https://mlsanity.com/paper/2312.07983/) (2023)
- [ASD Classification on Dynamic Brain Connectome using Temporal Random Walk with Transformer-based Dynamic Network Embedding](https://mlsanity.com/paper/2503.12366/) (2025)
- [iN2V: Bringing Transductive Node Embeddings to Inductive Graphs](https://mlsanity.com/paper/2506.05039/) (2025)

## Abstract (arXiv)

In this paper, we present subgraph2vec, a novel approach for learning latent representations of rooted subgraphs from large graphs inspired by recent advancements in Deep Learning and Graph Kernels. These latent representations encode semantic substructure dependencies in a continuous vector space, which is easily exploited by statistical models for tasks such as graph classification, clustering, link prediction and community detection. subgraph2vec leverages on local information obtained from neighbourhoods of nodes to learn their latent representations in an unsupervised fashion. We demonstrate that subgraph vectors learnt by our approach could be used in conjunction with classifiers such as CNNs, SVMs and relational data clustering algorithms to achieve significantly superior accuracies. Also, we show that the subgraph vectors could be used for building a deep learning variant of Weisfeiler-Lehman graph kernel. Our experiments on several benchmark and large-scale real-world datasets reveal that subgraph2vec achieves significant improvements in accuracies over existing graph kernels on both supervised and unsupervised learning tasks. Specifically, on two realworld program analysis tasks, namely, code clone and malware detection, subgraph2vec outperforms state-of-the-art kernels by more than 17% and 4%, respectively.