GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
arXiv:1906.12192
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.
As published in ICML 2020 proceedings
References in corpus (9)
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Pitfalls of Graph Neural Network Evaluation
- Predicting multicellular function through multi-layer tissue networks
- Layer Normalization
- Pay Less Attention with Lightweight and Dynamic Convolutions
- Relational Graph Attention Networks
- Open Vocabulary Learning on Source Code with a Graph-Structured Cache
- Fast Training of Sparse Graph Neural Networks on Dense Hardware
Cited by in corpus (9)
- Benchmarking Graph Neural Networks
- High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing
- Meta-Graph: Few Shot Link Prediction via Meta Learning
- GraphWorld: Fake Graphs Bring Real Insights for GNNs
- TreeCaps: Tree-Based Capsule Networks for Source Code Processing
- Embedding Graphs on Grassmann Manifold
- PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
- Deep Object Co-segmentation via Spatial-Semantic Network Modulation
- Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation