TabGraphs: A Benchmark and Strong Baselines for Learning on Graphs with Tabular Node Features

1 code implementation • 22 Sep 2024 • Gleb Bazhenov, Oleg Platonov, Liudmila Prokhorenkova

Thus, there is a critical difference between the data used in tabular and graph machine learning studies, which does not allow one to understand how successfully graph models can be transferred to tabular data.

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

3 code implementations • 22 Feb 2023 • Oleg Platonov, Denis Kuznedelev, Michael Diskin, Artem Babenko, Liudmila Prokhorenkova

Graphs without this property are called heterophilous, and it is typically assumed that specialized methods are required to achieve strong performance on such graphs.

Graph Representation Learning Node Classification

Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

no code implementations • NeurIPS 2023 • Oleg Platonov, Denis Kuznedelev, Artem Babenko, Liudmila Prokhorenkova

For this, we formalize desirable properties for a proper homophily measure and verify which measures satisfy which properties.

Informativeness Node Classification