Gated Graph Sequence Neural Networks

TL;DR

This paper introduces Gated Graph Sequence Neural Networks, a flexible model for learning from graph-structured data, demonstrating superior performance on AI and program verification tasks.

Contribution

It extends previous Graph Neural Networks by incorporating gated recurrent units and sequence output capabilities, improving learning on graph-structured inputs.

Findings

Achieves state-of-the-art results in program verification tasks.

Effectively models sequences on graph-structured data.

Outperforms traditional sequence models like LSTMs on graph tasks.

Abstract

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and modern optimization techniques and then extend to output sequences. The result is a flexible and broadly useful class of neural network models that has favorable inductive biases relative to purely sequence-based models (e.g., LSTMs) when the problem is graph-structured. We demonstrate the capabilities on some simple AI (bAbI) and graph algorithm learning tasks. We then show it achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.