# Learning Role-based Graph Embeddings

arXiv: https://arxiv.org/abs/1802.02896 · HTML: https://mlsanity.com/paper/1802.02896/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2018.

## Built on by (most cited first, 14 of 14)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Twitch Gamers: a Dataset for Evaluating Proximity Preserving and Structural Role-based Node Embeddings](https://mlsanity.com/paper/2101.03091/) (2021)
- [Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding](https://mlsanity.com/paper/2110.07582/) (2021)
- [BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection](https://mlsanity.com/paper/2303.18138/) (2023)
- [Generalizable Cross-Graph Embedding for GNN-based Congestion Prediction](https://mlsanity.com/paper/2111.05941/) (2021)
- [Neural Embedding: Learning the Embedding of the Manifold of Physics Data](https://mlsanity.com/paper/2208.05484/) (2022)
- [MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning](https://mlsanity.com/paper/2206.09280/) (2022)
- [Network representation learning: A macro and micro view](https://mlsanity.com/paper/2111.10772/) (2021)
- [Towards Improved Illicit Node Detection with Positive-Unlabelled Learning](https://mlsanity.com/paper/2303.02462/) (2023)
- [Aitchison Embeddings for Learning Compositional Graph Representations](https://mlsanity.com/paper/2605.00716/) (2026)
- [Unsupervised Framework for Evaluating and Explaining Structural Node Embeddings of Graphs](https://mlsanity.com/paper/2306.10770/) (2023)
- [Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models](https://mlsanity.com/paper/2605.11142/) (2026)
- [LAGOON: An Analysis Tool for Open Source Communities](https://mlsanity.com/paper/2201.11657/) (2022)
- [Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls](https://mlsanity.com/paper/2602.21342/) (2026)

## Abstract (arXiv)

Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes (if available). This is achieved by learning functions that generalize to new nodes and graphs. We show that our proposed framework is effective with an average AUC improvement of 16.55% while requiring on average 853x less space than existing methods on a variety of graphs.