Dynamic Graph Convolutional Networks Using the Tensor M-Product

Abstract

Many irregular domains such as social networks, financial transactions, neuron connections, and natural language constructs are represented using graph structures. In recent years, a variety of graph neural networks (GNNs) have been successfully applied for representation learning and prediction on such graphs. In many of the real-world applications, the underlying graph changes over time, however, most of the existing GNNs are inadequate for handling such dynamic graphs. In this paper we propose a novel technique for learning embeddings of dynamic graphs using a tensor algebra framework. Our method extends the popular graph convolutional network (GCN) for learning representations of dynamic graphs using the recently proposed tensor M-product technique. Theoretical results presented establish a connection between the proposed tensor approach and spectral convolution of tensors. The proposed method TM-GCN is consistent with the Message Passing Neural Network (MPNN) framework, accounting for both spatial and temporal message passing. Numerical experiments on real-world datasets demonstrate the performance of the proposed method for edge classification and link prediction tasks on dynamic graphs. We also consider an application related to the COVID-19 pandemic, and show how our method can be used for early detection of infected individuals from contact tracing data.

Accepted to SIAM International Conference on Data Mining (SDM) 2021

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Graph Neural Networks: A Review of Methods and Applications
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Graph analysis of functional brain networks: practical issues in translational neuroscience
• Scalable Graph Learning for Anti-Money Laundering: A First Look
• Dynamic Graph Representation Learning via Self-Attention Networks
• Novel methods for multilinear data completion and de-noising based on tensor-SVD
• COVI White Paper
• Tensor Graph Convolutional Networks for Text Classification

Cited by in corpus (2)

• Efficient Scaling of Dynamic Graph Neural Networks
• RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks