# Heterogeneous Graph Sparsification for Efficient Representation Learning

arXiv: https://arxiv.org/abs/2211.07518 · HTML: https://mlsanity.com/paper/2211.07518/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 14 Nov 2022.

## Builds on (most cited first, 5 of 5)

- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks](https://mlsanity.com/paper/1803.01848/) (2018)

## Built on by (most cited first, 1 of 1)

- [Heterogeneous Graph Condensation via Role-Aware Clustering](https://mlsanity.com/paper/2607.03097/) (2026)

## Abstract (arXiv)

Graph sparsification is a powerful tool to approximate an arbitrary graph and has been used in machine learning over homogeneous graphs. In heterogeneous graphs such as knowledge graphs, however, sparsification has not been systematically exploited to improve efficiency of learning tasks. In this work, we initiate the study on heterogeneous graph sparsification and develop sampling-based algorithms for constructing sparsifiers that are provably sparse and preserve important information in the original graphs. We have performed extensive experiments to confirm that the proposed method can improve time and space complexities of representation learning while achieving comparable, or even better performance in subsequent graph learning tasks based on the learned embedding.