Tensor Graph Convolutional Networks for Multi-Relational and Robust Learning
- 7 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 6535-6546
Abstract
The era of “data deluge” has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. Key aspects of the novel TGCN architecture are the dynamic adaptation to different relations in the tensor graph via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parameterization. The ultimate goal is to design a powerful learning architecture able to: discover complex and highly nonlinear data associations, combine (and select) multiple types of relations, scale gracefully with the graph size, and remain robust to perturbations on the graph edges. The proposed architecture is relevant not only in applications where the nodes are naturally involved in different relations (e.g., a multi-relational graph capturing family, friendship and work relations in a social network), but also in robust learning setups where the graph entails a certain level of uncertainty, and the different tensor slabs correspond to different versions (realizations) of the nominal graph. Numerical tests showcase that the proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.Keywords
All Related Versions
Funding Information
- University of Minnesota
- National Science Foundation (171141, 1500713, 1442686)
- Spanish Grants KLINILYCS (TEC2016-75361-R)
- SPGRAPH (PID2019-105032GB-I00)
- Instituto de Salud Carlos III (DTS17/00158)
This publication has 35 references indexed in Scilit:
- Predicting multicellular function through multi-layer tissue networksBioinformatics, 2017
- Deep Residual Learning for Image Recognition2016
- Outlier Analysis2015
- Multilayer networksJournal of Complex Networks, 2014
- An Improved Particle Swarm Optimization (PSO)–Based MPPT for PV With Reduced Steady-State OscillationIEEE Transactions on Power Electronics, 2012
- Deep Learning via Semi-supervised Embedding2012
- Network motifs: theory and experimental approachesNature Reviews Genetics, 2007
- Kernels and Regularization on Graphs2003
- Dithering with blue noiseProceedings of the IEEE, 1988
- Learning representations by back-propagating errorsNature, 1986