Gated Graph Sequence Neural Networks

TLDR

Graph‑structured data is common in chemistry, natural language semantics, social networks, and knowledge bases. The study investigates feature‑learning techniques for graph‑structured inputs. Building on prior Graph Neural Networks, we modify them to incorporate gated recurrent units and modern optimization, extend them to output sequences, and demonstrate their capabilities on simple AI (bAbI) and graph‑algorithm learning tasks. These models provide flexible, graph‑structured inductive biases over purely sequence‑based models and achieve state‑of‑the‑art performance on a program‑verification task requiring subgraph matching to abstract data structures.

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.