# RiWalk: Fast Structural Node Embedding via Role Identification

arXiv: https://arxiv.org/abs/1910.06541 · HTML: https://mlsanity.com/paper/1910.06541/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [A Survey on Role-Oriented Network Embedding](https://mlsanity.com/paper/2107.08379/) (2021)
- [Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs](https://mlsanity.com/paper/2309.02460/) (2023)
- [Representation Learning on Heterostructures via Heterogeneous Anonymous Walks](https://mlsanity.com/paper/2201.06972/) (2022)
- [Digraphwave: Scalable Extraction of Structural Node Embeddings via Diffusion on Directed Graphs](https://mlsanity.com/paper/2207.10149/) (2022)
- [Role Similarity Metric Based on Spanning Rooted Forest](https://mlsanity.com/paper/2110.07872/) (2021)
- [Can one hear the position of nodes?](https://mlsanity.com/paper/2211.06325/) (2022)
- [Omega-N: Interpretable Structural Node Descriptors and Their Applicability Domain](https://mlsanity.com/paper/2609.01633/) (2026)

## Abstract (arXiv)

Nodes performing different functions in a network have different roles, and these roles can be gleaned from the structure of the network. Learning latent representations for the roles of nodes helps to understand the network and to transfer knowledge across networks. However, most existing structural embedding approaches suffer from high computation and space cost or rely on heuristic feature engineering. Here we propose RiWalk, a flexible paradigm for learning structural node representations. It decouples the structural embedding problem into a role identification procedure and a network embedding procedure. Through role identification, rooted kernels with structural dependencies kept are built to better integrate network embedding methods. To demonstrate the effectiveness of RiWalk, we develop two different role identification methods named RiWalk-SP and RiWalk-WL respectively and employ random walk based network embedding methods. Experiments on within-network classification tasks show that our proposed algorithms achieve comparable performance with other baselines while being an order of magnitude more efficient. Besides, we also conduct across-network role classification tasks. The results show potential of structural embeddings in transfer learning. RiWalk is also scalable, making it capable of capturing structural roles in massive networks.