# Mixture of Link Predictors on Graphs

arXiv: https://arxiv.org/abs/2402.08583 · HTML: https://mlsanity.com/paper/2402.08583/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts.
- Builds on 30 of its 56 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Placed in

- Mixture-of-experts / [MoE for time series and graphs](https://mlsanity.com/moe/moe-for-time-series-and-graphs/)

## Builds on (most cited first, 30 of 30)

- [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)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Session-based Recommendation with Graph Neural Networks](https://mlsanity.com/paper/1811.00855/) (2018)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning](https://mlsanity.com/paper/2010.16103/) (2020)
- [Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks](https://mlsanity.com/paper/2203.00199/) (2022)
- [Graph Neural Networks for Link Prediction with Subgraph Sketching](https://mlsanity.com/paper/2209.15486/) (2022)
- [Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2206.04216/) (2022)
- [Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking](https://mlsanity.com/paper/2306.10453/) (2023)
- [Neural Common Neighbor with Completion for Link Prediction](https://mlsanity.com/paper/2302.00890/) (2023)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [Towards Understanding Mixture of Experts in Deep Learning](https://mlsanity.com/paper/2208.02813/) (2022)
- [Stacking Models for Nearly Optimal Link Prediction in Complex Networks](https://mlsanity.com/paper/1909.07578/) (2019)
- [Revisiting Link Prediction: A Data Perspective](https://mlsanity.com/paper/2310.00793/) (2023)
- [Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs](https://mlsanity.com/paper/2206.09144/) (2022)
- [LPFormer: An Adaptive Graph Transformer for Link Prediction](https://mlsanity.com/paper/2310.11009/) (2023)
- [Personalized PageRank to a Target Node, Revisited](https://mlsanity.com/paper/2006.11876/) (2020)
- [Link Prediction on Heterophilic Graphs via Disentangled Representation Learning](https://mlsanity.com/paper/2208.01820/) (2022)
- [Leveraging Node Attributes for Incomplete Relational Data](https://mlsanity.com/paper/1706.04289/) (2017)

## Built on by (most cited first, 10 of 10)

- [GiGL: Large-Scale Graph Neural Networks at Snapchat](https://mlsanity.com/paper/2502.15054/) (2025)
- [DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts](https://mlsanity.com/paper/2411.03025/) (2024)
- [TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2602.08592/) (2026)
- [Reconsidering the Performance of GAE in Link Prediction](https://mlsanity.com/paper/2411.03845/) (2024)
- [Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution](https://mlsanity.com/paper/2603.13360/) (2026)
- [Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction](https://mlsanity.com/paper/2504.06193/) (2025)
- [H2GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs](https://mlsanity.com/paper/2506.08298/) (2025)
- [Enhancing Contrastive Link Prediction With Edge Balancing Augmentation](https://mlsanity.com/paper/2508.14808/) (2025)
- [Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization](https://mlsanity.com/paper/2510.21207/) (2025)
- [Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning](https://mlsanity.com/paper/2609.08709/) (2026)

## Abstract (arXiv)

Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models that only apply the same pairwise information uniformly could achieve suboptimal performance. As a result, we propose a simple mixture of experts model Link-MoE for link prediction. Link-MoE utilizes various GNNs as experts and strategically selects the appropriate expert for each node pair based on various types of pairwise information. Experimental results across diverse real-world datasets demonstrate substantial performance improvement from Link-MoE. Notably, Link-MoE achieves a relative improvement of 18.71% on the MRR metric for the Pubmed dataset and 9.59% on the Hits@100 metric for the ogbl-ppa dataset, compared to the best baselines.