Few-shot Learning for Topic Modeling
This addresses the need for efficient topic modeling in scenarios with scarce data, though it is incremental as it builds on existing neural and EM-based approaches.
The paper tackles the problem of training topic models with limited data by proposing a neural network-based few-shot learning method that learns from just a few documents, achieving better perplexity than existing methods on three real-world text datasets.
Topic models have been successfully used for analyzing text documents. However, with existing topic models, many documents are required for training. In this paper, we propose a neural network-based few-shot learning method that can learn a topic model from just a few documents. The neural networks in our model take a small number of documents as inputs, and output topic model priors. The proposed method trains the neural networks such that the expected test likelihood is improved when topic model parameters are estimated by maximizing the posterior probability using the priors based on the EM algorithm. Since each step in the EM algorithm is differentiable, the proposed method can backpropagate the loss through the EM algorithm to train the neural networks. The expected test likelihood is maximized by a stochastic gradient descent method using a set of multiple text corpora with an episodic training framework. In our experiments, we demonstrate that the proposed method achieves better perplexity than existing methods using three real-world text document sets.