Gated Graph Sequence Neural Networks
This work addresses graph-structured data problems in domains like chemistry and AI, offering a flexible model with inductive biases, but it is incremental as it builds on existing Graph Neural Networks.
The authors tackled the problem of feature learning for graph-structured data by modifying Graph Neural Networks with gated recurrent units and extending them to output sequences, resulting in a model that achieves state-of-the-art performance on a program verification task.
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.