mlsanityData to 14 Oct 2026

Reconsidering the Performance of GAE in Link Prediction

arXiv 2411.03845 ↗First posted 6 Nov 2024cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Recent advancements in graph neural networks (GNNs) for link prediction have introduced sophisticated training techniques and model architectures. However, reliance on outdated baselines may exaggerate the benefits of these new approaches. To tackle this issue, we systematically explore Graph Autoencoders (GAEs) by applying model-agnostic tricks in recent methods and tuning hyperparameters. We find that a well-tuned GAE can match the performance of recent sophisticated models while offering superior computational efficiency on widely-used link prediction benchmarks. Our approach delivers substantial performance gains on datasets where structural information dominates and feature data is limited. Specifically, our GAE achieves a state-of-the-art Hits@100 score of 78.41% on the ogbl-ppa dataset. Furthermore, we examine the impact of various tricks to uncover the reasons behind our success and to guide the design of future methods. Our study emphasizes the critical need to update baselines for a more accurate assessment of progress in GNNs for link prediction. Our code is available at https://github.com/GraphPKU/Refined-GAE.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 6 Nov 2024.

Builds on

33 of 51 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2017Graph Attention Networkscited by 8,923
  6. 2017Inductive Representation Learning on Large Graphscited by 6,320
  7. 2018How Powerful are Graph Neural Networks?cited by 4,393
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  9. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  10. 2019Simplifying Graph Convolutional Networkscited by 1,477
  11. 2016Variational Graph Auto-Encoderscited by 1,382
  12. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
21 more
  1. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  2. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  3. 2020Simple and Deep Graph Convolutional Networkscited by 860
  4. 2018Link Prediction Based on Graph Neural Networkscited by 832
  5. 2020Inductive Representation Learning on Temporal Graphscited by 462
  6. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  7. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 242
  8. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  9. 2019Inductive Matrix Completion Based on Graph Neural Networkscited by 86
  10. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 85
  11. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  12. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  13. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  14. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  15. 2023Revisiting Link Prediction: A Data Perspectivecited by 29
  16. 2021Pairwise Learning for Neural Link Predictioncited by 23
  17. 2023Pure Message Passing Can Estimate Common Neighbor for Link Predictioncited by 18
  18. 2023LPFormer: An Adaptive Graph Transformer for Link Predictioncited by 17
  19. 2024Mixture of Link Predictors on Graphscited by 10
  20. 2024Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancementcited by 9
  21. 2023Efficient Link Prediction via GNN Layers Induced by Negative Samplingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Relatron: Automating Relational Machine Learning over Relational Databasescited by 2
  2. 2026Plain Transformers are Surprisingly Powerful Link Predictorscited by 0
  3. 2026A Survey on GNN-based Link Prediction: Techniques, Applications, and Challengescited by 0
  4. 2026Link prediction on multi-relational graphs from an influence propagation perspectivecited by 0