Residual Belief Propagation for Topic Modeling
This work addresses the need for faster training in LDA, particularly for online and parallel processing of massive datasets, offering an incremental improvement over existing algorithms.
The paper tackles the problem of slow convergence in training latent Dirichlet allocation (LDA) for topic modeling, presenting a residual belief propagation (RBP) algorithm that significantly reduces training time and achieves lower predictive perplexity compared to state-of-the-art methods.
Fast convergence speed is a desired property for training latent Dirichlet allocation (LDA), especially in online and parallel topic modeling for massive data sets. This paper presents a novel residual belief propagation (RBP) algorithm to accelerate the convergence speed for training LDA. The proposed RBP uses an informed scheduling scheme for asynchronous message passing, which passes fast-convergent messages with a higher priority to influence those slow-convergent messages at each learning iteration. Extensive empirical studies confirm that RBP significantly reduces the training time until convergence while achieves a much lower predictive perplexity than other state-of-the-art training algorithms for LDA, including variational Bayes (VB), collapsed Gibbs sampling (GS), loopy belief propagation (BP), and residual VB (RVB).