Keywords: Graph Neural Networks, Graph Representation Learning, Directed Acyclic Graphs, DAG, Inductive Bias
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 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.
One-sentence Summary: We propose DAGNN, a graph neural network tailored to directed acyclic graphs that outperforms conventional GNNs by leveraging the partial order as strong inductive bias besides other suitable architectural features.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) vthost/DAGNN](https://github.com/vthost/DAGNN)