A critical look at the evaluation of GNNs under heterophily: are we really making progress?

By Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, Liudmila Prokhorenkova. International Conference on Learning Representations, 2023

413 citations recorded by the source corpus.

Node classification is a classical graph machine learning task on which Graph Neural Networks (GNNs) have recently achieved strong results. However, it is often believed that standard GNNs only work well for homophilous graphs, i.e., graphs where edges tend to connect nodes of the same class. Graphs without this property are called heterophilous, and it is typically assumed that specialized methods are required to achieve strong performance on such graphs. In this work, we challenge this assumption. First, we show that the standard datasets used for evaluating heterophily-specific models have serious drawbacks, making results obtained by using them unreliable. The most significant of these drawbacks is the presence of a large number of duplicate nodes in the datasets Squirrel and Chameleon, which leads to train-test data leakage. We show that removing duplicate nodes strongly affects GNN performance on these datasets. Then, we propose a set of heterophilous graphs of varying properties that we believe can serve as a better benchmark for evaluating the performance of GNNs under heterophily. We show that standard GNNs achieve strong results on these heterophilous graphs, almost always outperforming specialized models. Our datasets and the code for reproducing our experiments are available at https://github.com/yandex-research/heterophilous-graphs

Subfields: Physiology, Pulmonary and Respiratory Medicine

View Paper: https://www.semanticscholar.org/paper/6ef892cd47300c56a72ff67bc7b87b43b3654e16

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

  1. Yixin Liu
  2. Shirui Pan
  3. Philip S. Yu
  4. Xin Zheng
  5. Miao Zhang
  6. Di Jin
  7. Charu C. Aggarwal
  8. Benjamin C. M. Fung

Citations in the corpus