dacaidi/lrfr

Official repository for the ICASSP 2024 paper 'Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning'.

PyTorch Implementation of the LRFR Algorithm for Continual Learning

As featured in our paper presented at ICASSP 2024:

Title: Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning

Authors: Zhenrong Liu, Yang Li, Yi Gong, Yik-Chung Wu

Email: [email protected]

Arxiv: https://arxiv.org/abs/2312.08740

Usage

sh LRFR.sh

Requirements: Python 3.9, PyTorch=2.0.0, tensorboardX

Citation and Acknowledgment

If you find our paper or code beneficial for your research or projects, please cite our paper:

@INPROCEEDINGS{10446458,
  author={Liu, Zhenrong and Li, Yang and Gong, Yi and Wu, Yik-Chung},
  booktitle={ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Learning a Low-Rank Feature Representation: Achieving Better Trade-Off Between Stability and Plasticity in Continual Learning}, 
  year={2024},
  pages={5885-5889},
  doi={10.1109/ICASSP48485.2024.10446458}}