# HONE: Higher-Order Network Embeddings

arXiv: https://arxiv.org/abs/1801.09303 · HTML: https://mlsanity.com/paper/1801.09303/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2018.

## Built on by (most cited first, 6 of 6)

- [Neural Predicting Higher-order Patterns in Temporal Networks](https://mlsanity.com/paper/2106.06039/) (2021)
- [Neural Graph Databases](https://mlsanity.com/paper/2209.09732/) (2022)
- [HOT: Higher-Order Dynamic Graph Representation Learning with Efficient Transformers](https://mlsanity.com/paper/2311.18526/) (2023)
- [Demystifying Higher-Order Graph Neural Networks](https://mlsanity.com/paper/2406.12841/) (2024)
- [Simplifying complex machine learning by linearly separable network embedding spaces](https://mlsanity.com/paper/2410.01865/) (2024)
- [Higher-Order Graph Databases](https://mlsanity.com/paper/2506.19661/) (2025)

## Abstract (arXiv)

This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs. The HONE framework is highly expressive and flexible with many interchangeable components. The experimental results demonstrate the effectiveness of learning higher-order network representations. In all cases, HONE outperforms recent embedding methods that are unable to capture higher-order structures with a mean relative gain in AUC of 19% (and up to 75% gain) across a wide variety of networks and embedding methods.