A Dynamic Linear Bias Incorporation Scheme for Nonnegative Latent Factor Analysis

High-Dimensional and Incomplete (HDI) data is commonly encountered in big data-related applications like social network services systems, which are concerning limited interactions among numerous nodes. Knowledge discovery from HDI data is a vital issue in the domain of data science due to their embedded rich patterns like node behaviors, where the fundamental task is to perform HDI data representation learning. Nonnegative Latent Factor Analysis (NLFA) models have proven to possess the superiority to address this issue, where a Linear Bias Incorporation (LBI) scheme is effective in preventing the model from the training overshooting and fluctuation for good convergence. However, existing LBI schemes are all statistic ones where the linear biases are fixed, which significantly restricts the scalability of the resultant NLFA model and results in loss of representation learning ability to HDI data. Motivated by the above discoveries, this paper innovatively presents a Dynamic Linear Bias Incorporation (DLBI) scheme. It firstly extends the linear bias vectors into matrices, and then builds a binary weight matrix to switch from the linear biases’ active states to their inactive states. The weight matrix’s each entry is manipulated between the binary states dynamically according to variation of the linear bias value, thereby establishing the dynamic linear biases for an NLFA model. Empirical studies on three HDI datasets from real applications indicate that the proposed DLBI-based NLFA outperforms state-of-the-art models in representation accuracy.