GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

TL;DR

GNN-FiLM introduces feature-wise linear modulation to enhance message passing in graph neural networks, improving performance on molecular graph regression and competing well on other tasks.

Contribution

The paper proposes GNN-FiLM, a novel GNN architecture that incorporates FiLM for feature-wise modulation, advancing GNN expressiveness and performance.

Findings

GNN-FiLM outperforms baseline models on molecular graph regression.

Differences between baseline GNNs are smaller than previously reported.

Hyperparameter tuning reduces performance gaps among models.

Abstract

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM). Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge. In GNN-FiLM, the representation of the target node of an edge is additionally used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information. Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based on re-implementations of baseline methods. Hyperparameters for all methods were found using extensive search, yielding somewhat surprising results: differences between baseline models are smaller than reported in the literature. Nonetheless, GNN-FiLM outperforms baseline methods on a regression task on molecular graphs and performs competitively on other tasks.