# Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices

arXiv: https://arxiv.org/abs/2306.00899 · HTML: https://mlsanity.com/paper/2306.00899/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 42 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 15 of 15)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [struc2vec: Learning Node Representations from Structural Identity](https://mlsanity.com/paper/1704.03165/) (2017)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Hyperspherical Variational Auto-Encoders](https://mlsanity.com/paper/1804.00891/) (2018)
- [Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning](https://mlsanity.com/paper/2010.16103/) (2020)
- [DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs](https://mlsanity.com/paper/2010.05337/) (2020)
- [Commonsense Knowledge Base Completion with Structural and Semantic Context](https://mlsanity.com/paper/1910.02915/) (2019)
- [FakeEdge: Alleviate Dataset Shift in Link Prediction](https://mlsanity.com/paper/2211.15899/) (2022)
- [Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning](https://mlsanity.com/paper/2005.10831/) (2020)

## Built on by (most cited first, 13 of 13)

- [Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning](https://mlsanity.com/paper/2406.16321/) (2024)
- [TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning](https://mlsanity.com/paper/2309.13885/) (2023)
- [On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks](https://mlsanity.com/paper/2409.17475/) (2024)
- [DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data](https://mlsanity.com/paper/2505.15074/) (2025)
- [Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/2406.13114/) (2024)
- [GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks](https://mlsanity.com/paper/2510.22451/) (2025)
- [Graph Prompting for Graph Learning Models: Recent Advances and Future Directions](https://mlsanity.com/paper/2506.08326/) (2025)
- [Link Prediction with Physics-Inspired Graph Neural Networks](https://mlsanity.com/paper/2402.14802/) (2024)
- [PROXI: Challenging the GNNs for Link Prediction](https://mlsanity.com/paper/2410.01802/) (2024)
- [Towards Understanding Link Predictor Generalizability Under Distribution Shifts](https://mlsanity.com/paper/2406.08788/) (2024)
- [Graph Neural Networks for O-RAN Mobility Management: A Link Prediction Approach](https://mlsanity.com/paper/2502.02170/) (2025)
- [Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks](https://mlsanity.com/paper/2602.03217/) (2026)
- [MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks](https://mlsanity.com/paper/2609.00696/) (2026)

## Abstract (arXiv)

While Graph Neural Networks (GNNs) are remarkably successful in a variety of high-impact applications, we demonstrate that, in link prediction, the common practices of including the edges being predicted in the graph at training and/or test have outsized impact on the performance of low-degree nodes. We theoretically and empirically investigate how these practices impact node-level performance across different degrees. Specifically, we explore three issues that arise: (I1) overfitting; (I2) distribution shift; and (I3) implicit test leakage. The former two issues lead to poor generalizability to the test data, while the latter leads to overestimation of the model's performance and directly impacts the deployment of GNNs. To address these issues in a systematic way, we introduce an effective and efficient GNN training framework, SpotTarget, which leverages our insight on low-degree nodes: (1) at training time, it excludes a (training) edge to be predicted if it is incident to at least one low-degree node; and (2) at test time, it excludes all test edges to be predicted (thus, mimicking real scenarios of using GNNs, where the test data is not included in the graph). SpotTarget helps researchers and practitioners adhere to best practices for learning from graph data, which are frequently overlooked even by the most widely-used frameworks. Our experiments on various real-world datasets show that SpotTarget makes GNNs up to 15x more accurate in sparse graphs, and significantly improves their performance for low-degree nodes in dense graphs.