Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining

TL;DR

SlimG is a simple, linear, and sparse model for semi-supervised node classification that outperforms complex GNNs in accuracy, robustness, scalability, and interpretability across diverse real-world graph datasets.

Contribution

The paper introduces SlimG, a carefully designed simple model that surpasses complex GNNs in accuracy, robustness, speed, and interpretability for various graph scenarios.

Findings

Achieves high accuracy on 10 out of 13 datasets.

Handles all graph data scenarios including noise and heterophily.

Up to 18 times faster training on large-scale graphs.

Abstract

How can we solve semi-supervised node classification in various graphs possibly with noisy features and structures? Graph neural networks (GNNs) have succeeded in many graph mining tasks, but their generalizability to various graph scenarios is limited due to the difficulty of training, hyperparameter tuning, and the selection of a model itself. Einstein said that we should "make everything as simple as possible, but not simpler." We rephrase it into the careful simplicity principle: a carefully-designed simple model can surpass sophisticated ones in real-world graphs. Based on the principle, we propose SlimG for semi-supervised node classification, which exhibits four desirable properties: It is (a) accurate, winning or tying on 10 out of 13 real-world datasets; (b) robust, being the only one that handles all scenarios of graph data (homophily, heterophily, random structure, noisy features, etc.); (c) fast and scalable, showing up to 18 times faster training in million-scale graphs; and (d) interpretable, thanks to the linearity and sparsity. We explain the success of SlimG through a systematic study of the designs of existing GNNs, sanity checks, and comprehensive ablation studies.