Anomaly detection within multivariate time series (MTS) is an essential task in both data
mining and service quality management. Many recent works on anomaly detection focus on …

Text Classification is the most essential and fundamental problem in Natural Language
Processing. While numerous recent text classification models applied the sequential deep …

To train an inference network jointly with a deep generative topic model, making it both
scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid …

We propose a Bayesian generative model for incorporating prior domain knowledge into
hierarchical topic modeling. Although embedded topic models (ETMs) and its variants have …

Hierarchical topic models such as the gamma belief network (GBN) have delivered
promising results in mining multi-layer document representations and discovering …

Abstract We propose a Topic Compositional Neural Language Model (TCNLM), a novel
method designed to simultaneously capture both the global semantic meaning and the local …

To infer multilayer deep representations of high-dimensional discrete and nonnegative real
vectors, we propose an augmentable gamma belief network (GBN) that factorizes each of its …

Deep topic models have shown an impressive ability to extract multi-layer document latent
representations and discover hierarchical semantically meaningful topics. However, most …

Embedding-based neural topic models have turned out to be a superior option for low-
resourced topic modeling. However, current approaches consider static word embeddings …

Constructing a graph with graph convolutional network (GCN) to explore the relational
structure of the data has attracted lots of interests in various tasks. However, for document …