# DiffETM: Diffusion Process Enhanced Embedded Topic Model

arXiv: https://arxiv.org/abs/2501.00862 · HTML: https://mlsanity.com/paper/2501.00862/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Builds on (most cited first, 10 of 10)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey](https://mlsanity.com/paper/1711.04305/) (2017)
- [Discovering Discrete Latent Topics with Neural Variational Inference](https://mlsanity.com/paper/1706.00359/) (2017)
- [Effective Neural Topic Modeling with Embedding Clustering Regularization](https://mlsanity.com/paper/2306.04217/) (2023)
- [Coherence-Aware Neural Topic Modeling](https://mlsanity.com/paper/1809.02687/) (2018)
- [DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM](https://mlsanity.com/paper/2310.15296/) (2023)
- [Coordinated Topic Modeling](https://mlsanity.com/paper/2210.08559/) (2022)
- [Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models](https://mlsanity.com/paper/2206.07960/) (2022)

## Built on by (most cited first, 1 of 1)

- [Discrete Diffusion in Large Language and Multimodal Models: A Survey](https://mlsanity.com/paper/2506.13759/) (2025)

## Abstract (arXiv)

The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization. However, this assumption oversimplifies the real document-topic distribution, limiting the model's performance. In response, we propose a novel method that introduces the diffusion process into the sampling process of document-topic distribution to overcome this limitation and maintain an easy optimization process. We validate our method through extensive experiments on two mainstream datasets, proving its effectiveness in improving topic modeling performance.