Tensor Graph Convolutional Networks for Multi-relational and Robust Learning

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.

arXiv commentGraph Convolutinal Networks, Robustness, Adversarial Attacks, Semi-supervised learning, Multi-relational/Heterogenous networks. arXiv admin note: text overlap with arXiv:1910.09590, arXiv:1811.02061

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• Explaining and Harnessing Adversarial Examples
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Multilayer Networks
• Adversarial Attacks on Neural Networks for Graph Data
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Predicting multicellular function through multi-layer tissue networks
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Real-time Power System State Estimation and Forecasting via Deep Neural Networks
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Filtering Random Graph Processes Over Random Time-Varying Graphs
• Adaptive Diffusions for Scalable Learning over Graphs

Cited by in corpus (5)

• Adversarial Attack and Defense on Graph Data: A Survey
• A Review of Graph Neural Networks and Their Applications in Power Systems
• Multiplex Graph Networks for Multimodal Brain Network Analysis
• Gauss-Newton Unrolled Neural Networks and Data-driven Priors for Regularized PSSE with Robustness
• PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs