# Neural Topic Modeling with Cycle-Consistent Adversarial Training

arXiv: https://arxiv.org/abs/2009.13971 · HTML: https://mlsanity.com/paper/2009.13971/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Topic Modelling Meets Deep Neural Networks: A Survey](https://mlsanity.com/paper/2103.00498/) (2021)
- [Contrastive Learning for Neural Topic Model](https://mlsanity.com/paper/2110.12764/) (2021)
- [A Survey on Neural Topic Models: Methods, Applications, and Challenges](https://mlsanity.com/paper/2401.15351/) (2024)
- [So Different Yet So Alike! Constrained Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.04093/) (2022)
- [Cycle Consistency Driven Object Discovery](https://mlsanity.com/paper/2306.02204/) (2023)
- [Improving Contextualized Topic Models with Negative Sampling](https://mlsanity.com/paper/2303.14951/) (2023)
- [Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification](https://mlsanity.com/paper/2402.18825/) (2024)
- [Adversarial Learning of Poisson Factorisation Model for Gauging Brand Sentiment in User Reviews](https://mlsanity.com/paper/2101.10150/) (2021)
- [Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models](https://mlsanity.com/paper/2206.07960/) (2022)
- [Dynamic Topic Language Model on Heterogeneous Children's Mental Health Clinical Notes](https://mlsanity.com/paper/2312.14180/) (2023)
- [Evaluating Negative Sampling Approaches for Neural Topic Models](https://mlsanity.com/paper/2503.18167/) (2025)

## Abstract (arXiv)

Advances on deep generative models have attracted significant research interest in neural topic modeling. The recently proposed Adversarial-neural Topic Model models topics with an adversarially trained generator network and employs Dirichlet prior to capture the semantic patterns in latent topics. It is effective in discovering coherent topics but unable to infer topic distributions for given documents or utilize available document labels. To overcome such limitations, we propose Topic Modeling with Cycle-consistent Adversarial Training (ToMCAT) and its supervised version sToMCAT. ToMCAT employs a generator network to interpret topics and an encoder network to infer document topics. Adversarial training and cycle-consistent constraints are used to encourage the generator and the encoder to produce realistic samples that coordinate with each other. sToMCAT extends ToMCAT by incorporating document labels into the topic modeling process to help discover more coherent topics. The effectiveness of the proposed models is evaluated on unsupervised/supervised topic modeling and text classification. The experimental results show that our models can produce both coherent and informative topics, outperforming a number of competitive baselines.