A Recurrent Graph Neural Network for Multi-Relational Data
release_seic75ndpndxbcbup46vjbrzsi
by
Vassilis N. Ioannidis, Antonio G. Marques, Georgios B. Giannakis
2018
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 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.
In text/plain
format
Archived Files and Locations
application/pdf 380.1 kB
file_ihkal4u2wjduhdc3wzldhx3kri
|
arxiv.org (repository) web.archive.org (webarchive) |
1811.02061v2
access all versions, variants, and formats of this works (eg, pre-prints)