Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks

TL;DR

This paper introduces a novel meta-aggregation scheme for 1-bit graph neural networks, enhancing their expressive power and performance through learnable, adaptive aggregation methods.

Contribution

The paper proposes two new meta neighborhood aggregators, GNA and ANA, that improve binarized GNNs by adaptively learning aggregation schemes, outperforming existing methods.

Findings

Meta aggregators significantly improve binarized GNN performance.

GNA learns to select the best aggregation scheme dynamically.

ANA combines multiple aggregators for enhanced expressiveness.

Abstract

In this paper, we study a novel meta aggregation scheme towards binarizing graph neural networks (GNNs). We begin by developing a vanilla 1-bit GNN framework that binarizes both the GNN parameters and the graph features. Despite the lightweight architecture, we observed that this vanilla framework suffered from insufficient discriminative power in distinguishing graph topologies, leading to a dramatic drop in performance. This discovery motivates us to devise meta aggregators to improve the expressive power of vanilla binarized GNNs, of which the aggregation schemes can be adaptively changed in a learnable manner based on the binarized features. Towards this end, we propose two dedicated forms of meta neighborhood aggregators, an exclusive meta aggregator termed as Greedy Gumbel Neighborhood Aggregator (GNA), and a diffused meta aggregator termed as Adaptable Hybrid Neighborhood Aggregator (ANA). GNA learns to exclusively pick one single optimal aggregator from a pool of candidates, while ANA learns a hybrid aggregation behavior to simultaneously retain the benefits of several individual aggregators. Furthermore, the proposed meta aggregators may readily serve as a generic plugin module into existing full-precision GNNs. Experiments across various domains demonstrate that the proposed method yields results superior to the state of the art.