GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
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 used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information. Different GNN architectures are compared in extensive experiments on three tasks from the literature, using re-implementations of many baseline methods. Hyperparameters for all methods were found using extensive search, yielding somewhat surprising results: differences between state of the art models are much smaller than reported in the literature and well-known simple baselines that are often not compared to perform better than recently proposed GNN variants. Nonetheless, GNN-FiLM outperforms these methods on a regression task on molecular graphs and performs competitively on other tasks.
BibTeX
@InProceedings{pmlr-v119-brockschmidt20a,
title = {{GNN}-{F}i{LM}: Graph Neural Networks with Feature-wise Linear Modulation},
author = {Brockschmidt, Marc},
booktitle = {Proceedings of the 37th International Conference on Machine Learning},
pages = {1144--1152},
year = {2020},
editor = {III, Hal Daumé and Singh, Aarti},
volume = {119},
series = {Proceedings of Machine Learning Research},
month = {13--18 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v119/brockschmidt20a/brockschmidt20a.pdf},
url = {https://proceedings.mlr.press/v119/brockschmidt20a.html},
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 used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information. Different GNN architectures are compared in extensive experiments on three tasks from the literature, using re-implementations of many baseline methods. Hyperparameters for all methods were found using extensive search, yielding somewhat surprising results: differences between state of the art models are much smaller than reported in the literature and well-known simple baselines that are often not compared to perform better than recently proposed GNN variants. Nonetheless, GNN-FiLM outperforms these methods on a regression task on molecular graphs and performs competitively on other tasks.}
}