Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

by   Juanhui Li, et al.

Link prediction attempts to predict whether an unseen edge exists based on only a portion of edges of a graph. A flurry of methods have been introduced in recent years that attempt to make use of graph neural networks (GNNs) for this task. Furthermore, new and diverse datasets have also been created to better evaluate the effectiveness of these new models. However, multiple pitfalls currently exist that hinder our ability to properly evaluate these new methods. These pitfalls mainly include: (1) Lower than actual performance on multiple baselines, (2) A lack of a unified data split and evaluation metric on some datasets, and (3) An unrealistic evaluation setting that uses easy negative samples. To overcome these challenges, we first conduct a fair comparison across prominent methods and datasets, utilizing the same dataset and hyperparameter search settings. We then create a more practical evaluation setting based on a Heuristic Related Sampling Technique (HeaRT), which samples hard negative samples via multiple heuristics. The new evaluation setting helps promote new challenges and opportunities in link prediction by aligning the evaluation with real-world situations. Our implementation and data are available at https://github.com/Juanhui28/HeaRT


page 1

page 2

page 3

page 4


Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Graph Neural Networks (GNNs) have been widely applied to various fields ...

Towards Better Evaluation for Dynamic Link Prediction

There has been recent success in learning from static graphs, but despit...

Edge Proposal Sets for Link Prediction

Graphs are a common model for complex relational data such as social net...

Improving Inductive Link Prediction Using Hyper-Relational Facts

For many years, link prediction on knowledge graphs (KGs) has been a pur...

Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks

We present Wiki-CS, a novel dataset derived from Wikipedia for benchmark...

BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks

To handle graphs in which features or connectivities are evolving over t...

Interpretable and Fair Comparison of Link Prediction or Entity Alignment Methods with Adjusted Mean Rank

In this work, we take a closer look at the evaluation of two families of...

Please sign up or login with your details

Forgot password? Click here to reset