GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
This work addresses a specific bottleneck in GNNs for researchers and practitioners in graph-based machine learning, though it is incremental as it builds on existing GNN paradigms with a novel modulation technique.
The paper tackles the problem of improving Graph Neural Networks (GNNs) by introducing GNN-FiLM, which uses feature-wise linear modulation to incorporate target node representations for modulating incoming messages, resulting in outperforming baseline methods on a molecular graph regression task and competitive performance on other tasks.
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.