Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration

TL;DR

This paper introduces GraphAC, a task-agnostic framework for evaluating GNNs using adversarial collaboration and contrastive self-supervision, providing a reliable alternative to dataset-specific benchmarks.

Contribution

It proposes a novel, task-agnostic evaluation method for GNNs that does not rely on data augmentations, using a new objective called Competitive Barlow Twins.

Findings

Successfully distinguishes GNNs of different expressiveness

Operates without data augmentations

Provides a stable and principled evaluation framework

Abstract

It has been increasingly demanding to develop reliable methods to evaluate the progress of Graph Neural Network (GNN) research for molecular representation learning. Existing GNN benchmarking methods for molecular representation learning focus on comparing the GNNs' performances on some node/graph classification/regression tasks on certain datasets. However, there lacks a principled, task-agnostic method to directly compare two GNNs. Additionally, most of the existing self-supervised learning works incorporate handcrafted augmentations to the data, which has several severe difficulties to be applied on graphs due to their unique characteristics. To address the aforementioned issues, we propose GraphAC (Graph Adversarial Collaboration) -- a conceptually novel, principled, task-agnostic, and stable framework for evaluating GNNs through contrastive self-supervision. We introduce a novel objective function: the Competitive Barlow Twins, that allow two GNNs to jointly update themselves from direct competitions against each other. GraphAC succeeds in distinguishing GNNs of different expressiveness across various aspects, and has demonstrated to be a principled and reliable GNN evaluation method, without necessitating any augmentations.