A Recurrent Graph Neural Network for Multi-Relational Data
This work addresses the need for scalable graph-based learning methods in disciplines like sociology and biology, though it appears incremental as it builds on existing neural network and graph learning approaches.
The authors tackled the problem of scalable semi-supervised learning from multi-relational data by introducing a graph recurrent neural network (GRNN) that dynamically adapts to different relations and uses graph-based regularizers, achieving performance gains over competing alternatives in numerical tests with real datasets.
The era of data deluge has sparked the interest in graph-based learning methods in a number of disciplines such as sociology, biology, neuroscience, or engineering. In this paper, we introduce a graph recurrent neural network (GRNN) for scalable semi-supervised learning from multi-relational data. Key aspects of the novel GRNN architecture are the use of multi-relational graphs, the dynamic adaptation to the different relations via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parametrization. Our ultimate goal is to design a powerful learning architecture able to: discover complex and highly non-linear data associations, combine (and select) multiple types of relations, and scale gracefully with respect to the size of the graph. Numerical tests with real data sets corroborate the design goals and illustrate the performance gains relative to competing alternatives.