Dynamically Weighted Directed Network Link Prediction Using Tensor Ring Decomposition

A Dynamically Weighted Directed Network (DWDN) is usually used to describe a complex interaction system, such as the Internet of Things, where a weighted directed link denotes a specific interaction between a pair of entities. Typically, there are numerous missing links in a DWDN due to practical limitations. A Latent Factorization of Tensors (LFT)-based link prediction method proves to be effective in predicting weighted directed links. However, current LFT-based predictor is often built based on the Canonical Polyadic (CP) decomposition, its prediction ability is limited due to its small latent feature space. To address this issue, this work proposes a Tensor Ring decomposition-based Biased Latent-factorization-of-tensors (TRBL) model with three interesting ideas: 1) adopting tensor ring decomposition to build an LFT model for obtaining a larger latent feature space; 2) utilizing linear biases to model data fluctuations for boosting prediction accuracy; and 3) introducing the single latent factor-dependent, nonnegative and multiplicative update on tensor algorithm for achieving fast convergence. Experimental studies on four real DWDNs demonstrate that compared with state-of-the-art models, the proposed TRBL model achieves higher accuracy and competitive convergence rate on predicting the missing weighted directed links of a DWDN.