# Link Prediction on Heterophilic Graphs via Disentangled Representation Learning

arXiv: https://arxiv.org/abs/2208.01820 · HTML: https://mlsanity.com/paper/2208.01820/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 49 references that are in the map.
- First posted on arXiv 3 Aug 2022.

## Builds on (most cited first, 26 of 26)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods](https://mlsanity.com/paper/2110.14446/) (2021)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Graph Neural Networks with Heterophily](https://mlsanity.com/paper/2009.13566/) (2020)
- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [Large-Scale Learnable Graph Convolutional Networks](https://mlsanity.com/paper/1808.03965/) (2018)
- [New Benchmarks for Learning on Non-Homophilous Graphs](https://mlsanity.com/paper/2104.01404/) (2021)
- [Factorizable Graph Convolutional Networks](https://mlsanity.com/paper/2010.05421/) (2020)
- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [Independence Promoted Graph Disentangled Networks](https://mlsanity.com/paper/1911.11430/) (2019)
- [Exploring Edge Disentanglement for Node Classification](https://mlsanity.com/paper/2202.11245/) (2022)
- [Graph-Based Recommendation System](https://mlsanity.com/paper/1808.00004/) (2018)

## Built on by (most cited first, 13 of 13)

- [The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges](https://mlsanity.com/paper/2407.09618/) (2024)
- [Mixture of Link Predictors on Graphs](https://mlsanity.com/paper/2402.08583/) (2024)
- [On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks](https://mlsanity.com/paper/2409.17475/) (2024)
- [Imbalanced Node Classification Beyond Homophilic Assumption](https://mlsanity.com/paper/2304.14635/) (2023)
- [Heterophilic Graph Neural Networks Optimization with Causal Message-passing](https://mlsanity.com/paper/2411.13821/) (2024)
- [Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network](https://mlsanity.com/paper/2403.17351/) (2024)
- [3D-IDS: Doubly Disentangled Dynamic Intrusion Detection](https://mlsanity.com/paper/2307.11079/) (2023)
- [Link Prediction with Physics-Inspired Graph Neural Networks](https://mlsanity.com/paper/2402.14802/) (2024)
- [PROXI: Challenging the GNNs for Link Prediction](https://mlsanity.com/paper/2410.01802/) (2024)
- [Attribute-Enhanced Similarity Ranking for Sparse Link Prediction](https://mlsanity.com/paper/2412.00261/) (2024)
- [Representation Learning of Complex Assemblies, An Effort to Improve Corporate Scope 3 Emissions Calculation](https://mlsanity.com/paper/2409.03769/) (2024)
- [SCNode: Spatial and Contextual Coordinates for Graph Representation Learning](https://mlsanity.com/paper/2410.02158/) (2024)
- [A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges](https://mlsanity.com/paper/2607.16198/) (2026)

## Abstract (arXiv)

Link prediction is an important task that has wide applications in various domains. However, the majority of existing link prediction approaches assume the given graph follows homophily assumption, and designs similarity-based heuristics or representation learning approaches to predict links. However, many real-world graphs are heterophilic graphs, where the homophily assumption does not hold, which challenges existing link prediction methods. Generally, in heterophilic graphs, there are many latent factors causing the link formation, and two linked nodes tend to be similar in one or two factors but might be dissimilar in other factors, leading to low overall similarity. Thus, one way is to learn disentangled representation for each node with each vector capturing the latent representation of a node on one factor, which paves a way to model the link formation in heterophilic graphs, resulting in better node representation learning and link prediction performance. However, the work on this is rather limited. Therefore, in this paper, we study a novel problem of exploring disentangled representation learning for link prediction on heterophilic graphs. We propose a novel framework DisenLink which can learn disentangled representations by modeling the link formation and perform factor-aware message-passing to facilitate link prediction. Extensive experiments on 13 real-world datasets demonstrate the effectiveness of DisenLink for link prediction on both heterophilic and hemophiliac graphs. Our codes are available at https://github.com/sjz5202/DisenLink