Skip to yearly menu bar Skip to main content


Bayesian Deep Embedding Topic Meta-Learner

Zhibin Duan · Yishi Xu · Jianqiao Sun · Bo Chen · Wenchao Chen · CHAOJIE WANG · Mingyuan Zhou

Hall E #812

Keywords: [ PM: Variational Inference ] [ PM: Graphical Models ] [ PM: Bayesian Models and Methods ] [ Probabilistic Methods ]


Existing deep topic models are effective in capturing the latent semantic structures in textual data but usually rely on a plethora of documents. This is less than satisfactory in practical applications when only a limited amount of data is available. In this paper, we propose a novel framework that efficiently solves the problem of topic modeling under the small data regime. Specifically, the framework involves two innovations: a bi-level generative model that aims to exploit the task information to guide the document generation, and a topic meta-learner that strives to learn a group of global topic embeddings so that fast adaptation to the task-specific topic embeddings can be achieved with a few examples. We apply the proposed framework to a hierarchical embedded topic model and achieve better performance than various baseline models on diverse experiments, including few-shot topic discovery and few-shot document classification.

Chat is not available.