Name
Abstract | ||
|---|---|---|
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 semisupervised 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 datasets corroborate the design goals and illustrate the performance gains relative to competing alternatives. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/icassp.2019.8682836 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Deep neural networks, graph recurrent neural networks, graph signals, multi-relational graphs | Numerical tests,Architecture,Data set,Relational database,Graph neural networks,Recurrent neural network,Artificial intelligence,Smoothness,Machine learning,Mathematics,Scalability | Journal |
Volume | ISSN | Citations |
abs/1811.02061 | 1520-6149 | 1 |
PageRank | References | Authors |
0.36 | 10 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Vassilis N. Ioannidis | 1 | 14 | 7.34 |
| Antonio G. Marqués | 2 | 254 | 33.71 |
| G. B. Giannakis | 3 | 11464 | 1206.47 |