https://github.com/Arnie0426/FastDTM

Repo for MCMC based Dynamic Topic Model
https://github.com/Arnie0426/FastDTM

Last synced: about 1 month ago
JSON representation

Repo for MCMC based Dynamic Topic Model

• Host: GitHub
• URL: https://github.com/Arnie0426/FastDTM
• Owner: Arnie0426
• Created: 2017-01-17T01:49:28.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2017-09-02T06:07:57.000Z (over 7 years ago)
• Last Synced: 2024-08-03T18:21:02.804Z (4 months ago)
• Language: C++
• Size: 2.66 MB
• Stars: 14
• Watchers: 3
• Forks: 7
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-topic-models - FastDTM - Scalable C++ implementation using Gibbs sampling with Stochastic Gradient Langevin Dynamics (MCMC-based) [:page_facing_up:](https://arxiv.org/pdf/1602.06049.pdf) (Models / Dynamic Topic Model (DTM) [:page_facing_up:](https://dl.acm.org/doi/pdf/10.1145/1143844.1143859))

README

        
# FastDTM

Repo for MCMC based Dynamic Topic Model.

This code has Eigen dependency. Before running this code, please make sure you update the CMakeLists to include the Eigen directory. All of this research was done at Tsinghua University in the [TSAIL](http://ml.cs.tsinghua.edu.cn/) group.

### To-do list

- [ ] Multithreaded implementation.

- [ ] Create Python wrapper for the code for easier usage.

- [ ] Create a DTM python module that can be easily pip installed.

### License

MIT


### Reference

If you find this implementation useful, please cite:

A Bhadury, J Chen, J Zhu, and Shixia Liu. Scaling up Dynamic Topic Models. In Proceedings of

the 25th International Conference on the World Wide Web, 2016.