Directed Acyclic Graph Neural Networks
arXiv:2101.07965
Abstract
Graph-structured data ubiquitously appears in science and engineering. Graph neural networks (GNNs) are designed to exploit the relational inductive bias exhibited in graphs; they have been shown to outperform other forms of neural networks in scenarios where structure information supplements node features. The most common GNN architecture aggregates information from neighborhoods based on message passing. Its generality has made it broadly applicable. In this paper, we focus on a special, yet widely used, type of graphs -- DAGs -- and inject a stronger inductive bias -- partial ordering -- into the neural network design. We propose the \emph{directed acyclic graph neural network}, DAGNN, an architecture that processes information according to the flow defined by the partial order. DAGNN can be considered a framework that entails earlier works as special cases (e.g., models for trees and models updating node representations recurrently), but we identify several crucial components that prior architectures lack. We perform comprehensive experiments, including ablation studies, on representative DAG datasets (i.e., source code, neural architectures, and probabilistic graphical models) and demonstrate the superiority of DAGNN over simpler DAG architectures as well as general graph architectures.
ICLR 2021. Code is available at https://github.com/vthost/DAGNN
References in corpus (10)
- Neural Message Passing for Quantum Chemistry
- Modeling polypharmacy side effects with graph convolutional networks
- Fast Graph Representation Learning with PyTorch Geometric
- A simple neural network module for relational reasoning
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Learning to Simulate Complex Physics with Graph Networks
- Learning Deep Generative Models of Graphs
- What Can Neural Networks Reason About?
- Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling