mlsanityData to 7 Oct 2026

Mixture of Link Predictors on Graphs

arXiv 2402.08583 ↗First posted 13 Feb 2024cs.LGcited by 10

On the map: Mixture-of-experts → MoE for time series and graphs

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.

Key facts. Cited by 10 papers in the map (data through 7 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.

Builds on

30 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling6 Apr

Other references · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  9. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  10. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
  11. 2018Link Prediction Based on Graph Neural Networkscited by 829
  12. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
17 more
  1. 2019Multi-scale Attributed Node Embeddingcited by 543
  2. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  3. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  4. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 148
  5. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  6. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  7. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  8. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  9. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  10. 2022Towards Understanding Mixture of Experts in Deep Learningcited by 52
  11. 2019Stacking Models for Nearly Optimal Link Prediction in Complex Networkscited by 35
  12. 2023Revisiting Link Prediction: A Data Perspectivecited by 29
  13. 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
  14. 2023LPFormer: An Adaptive Graph Transformer for Link Predictioncited by 17
  15. 2020Personalized PageRank to a Target Node, Revisitedcited by 16
  16. 2022Link Prediction on Heterophilic Graphs via Disentangled Representation Learningcited by 13
  17. 2017Leveraging Node Attributes for Incomplete Relational Datacited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 3.

10 papers.

  1. 2025GiGL: Large-Scale Graph Neural Networks at Snapchatcited by 8
  2. 2024DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Expertscited by 7
  3. 2026TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Modelscited by 5
  4. 2024Reconsidering the Performance of GAE in Link Predictioncited by 4
  5. 2026Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolutioncited by 1
  6. 2025Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Predictioncited by 0
  7. 2025H2GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphscited by 0
  8. 2025Enhancing Contrastive Link Prediction With Edge Balancing Augmentationcited by 0
  9. 2025Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specializationcited by 0
  10. 2026Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
  2. 2025Heuristic-Informed Mixture of Experts for Link Prediction in Multilayer Networks
  3. 2024Mixture of Experts for Node Classification
  4. 2025Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
  5. 2024Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
  6. 2026Early-Exit Graph Neural Networks for Link Prediction
  7. 2025GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models
  8. 2026Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification