# Line Graph Neural Networks for Link Prediction

arXiv: https://arxiv.org/abs/2010.10046 · HTML: https://mlsanity.com/paper/2010.10046/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2020.

## Built on by (most cited first, 30 of 89)

- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [GraphEBM: Molecular Graph Generation with Energy-Based Models](https://mlsanity.com/paper/2102.00546/) (2021)
- [Learning from Counterfactual Links for Link Prediction](https://mlsanity.com/paper/2106.02172/) (2021)
- [Message passing all the way up](https://mlsanity.com/paper/2202.11097/) (2022)
- [Linkless Link Prediction via Relational Distillation](https://mlsanity.com/paper/2210.05801/) (2022)
- [Graph Lifelong Learning: A Survey](https://mlsanity.com/paper/2202.10688/) (2022)
- [Class-Imbalanced Graph Learning without Class Rebalancing](https://mlsanity.com/paper/2308.14181/) (2023)
- [Towards Effective and General Graph Unlearning via Mutual Evolution](https://mlsanity.com/paper/2401.11760/) (2024)
- [Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection](https://mlsanity.com/paper/2212.12488/) (2022)
- [AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneity](https://mlsanity.com/paper/2401.11750/) (2024)
- [Cycle Representation Learning for Inductive Relation Prediction](https://mlsanity.com/paper/2110.02510/) (2021)
- [Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models](https://mlsanity.com/paper/2404.15625/) (2024)
- [Continual Learning on Graphs: Challenges, Solutions, and Opportunities](https://mlsanity.com/paper/2402.11565/) (2024)
- [GrOVe: Ownership Verification of Graph Neural Networks using Embeddings](https://mlsanity.com/paper/2304.08566/) (2023)
- [Towards Semi-supervised Universal Graph Classification](https://mlsanity.com/paper/2305.19598/) (2023)
- [Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications](https://mlsanity.com/paper/2207.11812/) (2022)
- [Line Graph Contrastive Learning for Link Prediction](https://mlsanity.com/paper/2210.13795/) (2022)
- [Knowledge Graph Completion with Counterfactual Augmentation](https://mlsanity.com/paper/2302.13083/) (2023)
- [Link Prediction with Non-Contrastive Learning](https://mlsanity.com/paper/2211.14394/) (2022)
- [ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance](https://mlsanity.com/paper/2312.08852/) (2023)
- [Sampling Enclosing Subgraphs for Link Prediction](https://mlsanity.com/paper/2206.12004/) (2022)
- [Learning Hypergraphs From Signals With Dual Smoothness Prior](https://mlsanity.com/paper/2211.01717/) (2022)
- [RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks](https://mlsanity.com/paper/2307.07840/) (2023)
- [SupplyGraph: A Benchmark Dataset for Supply Chain Planning using Graph Neural Networks](https://mlsanity.com/paper/2401.15299/) (2024)
- [Vertical Federated Learning: Taxonomies, Threats, and Prospects](https://mlsanity.com/paper/2302.01550/) (2023)
- [Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials](https://mlsanity.com/paper/2305.19872/) (2023)
- [LPNL: Scalable Link Prediction with Large Language Models](https://mlsanity.com/paper/2401.13227/) (2024)
- [Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and Benchmarks](https://mlsanity.com/paper/2411.08550/) (2024)
- [BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction](https://mlsanity.com/paper/2204.09508/) (2022)
- [Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2206.09567/) (2022)

## Abstract (arXiv)

We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. With the advances of deep learning, current link prediction methods commonly compute features from subgraphs centered at two neighboring nodes and use the features to predict the label of the link between these two nodes. In this formalism, a link prediction problem is converted to a graph classification task. In order to extract fixed-size features for classification, graph pooling layers are necessary in the deep learning model, thereby incurring information loss. To overcome this key limitation, we propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task. Experimental results on fourteen datasets from different applications demonstrate that our proposed method consistently outperforms the state-of-the-art methods, while it has fewer parameters and high training efficiency.