mlsanityData to 7 Oct 2026

Early-Exit Graph Neural Networks for Link Prediction

arXiv 2606.22167 ↗First posted 20 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks are great for link prediction in various network-like structures; however, the question of their speed/quality tradeoff has been barely studied. While in practice the time it takes to do inference matters little for small benchmarks, the latency does limit applicability in large-scale domains. In this work, we explore early-exiting strategies that can be applied to Graph Neural Networks to solve the problem of link-prediction faster. We use no auxiliary losses to enforce early exiting, allowing it to emerge as an implicit property of the architecture. We show that our method enables early exiting in several setups, moving the Pareto frontier on the HeaRT benchmark for GCN and SAS-GNN backbones. Our findings show that inference speed of GNNs on many link-prediction problems can be improved, while losing little, or even winning in terms of prediction quality. The code is available in our repository: https://github.com/knyazer/link_prediction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 11 references that are in the map. First posted on arXiv 20 Jun 2026.

Builds on

10 of 11 references.

References · 10

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  4. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
  5. 2022Graph-Coupled Oscillator Networkscited by 123
  6. 2020Why should we add early exits to neural networks?cited by 70
  7. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  8. 2020Adaptive Propagation Graph Convolutional Networkcited by 31
  9. 2021SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networkscited by 6
  10. 2025Early-Exit Graph Neural Networkscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
  2. 2025A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
  3. 2024Acceleration Algorithms in GNNs: A Survey
  4. 2024Mixture of Link Predictors on Graphs
  5. 2022Efficient Graph Neural Network Inference at Large Scale
  6. 2023Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagation
  7. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
  8. 2024Improving global awareness of linkset predictions using Cross-Attentive Modulation tokens