DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks

Abstract

Classical network embeddings create a low dimensional representation of the learned relationships between features across nodes. Such embeddings are important for tasks such as link prediction and node classification. In the current paper, we consider low dimensional embeddings of dynamic networks, that is a family of time varying networks where there exist both temporal and spatial link relationships between nodes. We present novel embedding methods for a dynamic network based on higher order tensor decompositions for tensorial representations of the dynamic network. In one sense, our embeddings are analogous to spectral embedding methods for static networks. We provide a rationale for our algorithms via a mathematical analysis of some potential reasons for their effectiveness. Finally, we demonstrate the power and efficiency of our approach by comparing our algorithms' performance on the link prediction task against an array of current baseline methods across three distinct real-world dynamic networks.

arXiv comment35 pages

References in corpus (13)

• Distributed Representations of Words and Phrases and their Compositionality
• Tensor Decomposition for Signal Processing and Machine Learning
• Diffusion dynamics on multiplex networks
• Variational Graph Auto-Encoders
• Knowledge Graph Embedding for Link Prediction: A Comparative Analysis
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• Spectral properties of the Laplacian of multiplex networks
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
• Estimation of Simultaneously Sparse and Low Rank Matrices
• Tensor Spectral Clustering for Partitioning Higher-order Network Structures
• Variational Graph Recurrent Neural Networks
• Characterization of multiple topological scales in multiplex networks through supra-Laplacian eigengaps
• Improved supervised prediction of aging-related genes via weighted dynamic network analysis