Skip to content

[ECML PKDD 2025] Official implementation of "PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval"

License

Notifications You must be signed in to change notification settings

LouisDo2108/PromptDSI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval

This is the official implementation of the paper PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval.

Environments

We use PyTorch 2.1.2+cu118 and Python 3.8.18. Please check requirements.txt for required packages.

Citation

If you find our code or the paper useful, please cite the paper:

@article{huynh2024promptdsi,
  title={Promptdsi: Prompt-based rehearsal-free instance-wise incremental learning for document retrieval},
  author={Huynh, Tuan-Luc and Vu, Thuy-Trang and Wang, Weiqing and Wei, Yinwei and Le, Trung and Gasevic, Dragan and Li, Yuan-Fang and Do, Thanh-Toan},
  journal={arXiv preprint arXiv:2406.12593},
  year={2024}
}

Contact

If you have any questions, please open an issue mentioning @LouisDo2108 or send an email to tuan.huynh1[at]monash.edu

Acknowledgements

This repository is based on the awesome works of IncDSI along with PCL methods, including L2P, DualPrompt, CODAPrompt, and HiDe-Prompt. We also thanks the authors of BERTopic for providing useful guides for topic modeling.

About

[ECML PKDD 2025] Official implementation of "PromptDSI: Prompt-based Rehearsal-free Continual Learning for Document Retrieval"

Topics

Resources

License

Stars

Watchers

Forks