Directed Acyclic Graph Neural Networks
This work addresses the need for more effective neural network models for DAG-structured data, which is common in fields like software engineering and machine learning, though it appears incremental by building on prior GNN methods.
The paper tackled the problem of processing directed acyclic graphs (DAGs) by proposing DAGNN, a neural network architecture that incorporates partial ordering as an inductive bias, and demonstrated its superiority over simpler DAG and general graph architectures in experiments on datasets like source code and neural architectures.
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.