Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention

TL;DR

This paper introduces GRASS, a novel GNN architecture that combines encoding, rewiring, and attention mechanisms to improve structural information capture and long-range propagation, achieving state-of-the-art results.

Contribution

GRASS integrates RRWP encoding, graph rewiring with random regular graphs, and a new attention mechanism, advancing GNN performance on benchmark datasets.

Findings

Achieves state-of-the-art results on multiple benchmarks

Reduces mean absolute error by 20.3% on ZINC dataset

Effectively captures long-range structural information

Abstract

Graph Neural Networks (GNNs) have become important tools for machine learning on graph-structured data. In this paper, we explore the synergistic combination of graph encoding, graph rewiring, and graph attention, by introducing Graph Attention with Stochastic Structures (GRASS), a novel GNN architecture. GRASS utilizes relative random walk probabilities (RRWP) encoding and a novel decomposed variant (D-RRWP) to efficiently capture structural information. It rewires the input graph by superimposing a random regular graph to enhance long-range information propagation. It also employs a novel additive attention mechanism tailored for graph-structured data. Our empirical evaluations demonstrate that GRASS achieves state-of-the-art performance on multiple benchmark datasets, including a 20.3% reduction in mean absolute error on the ZINC dataset.