Knowledge-guided prompt-based continual learning: Aligning task-prompts through contrastive hard negatives
Authors:
- Heng-Yang LuHLHeng-Yang Lu
- Long-Kang LinLLLong-Kang Lin
- Chenyou FanCFChenyou Fan
- Chongjun WangCWChongjun Wang
- Wei FangWFWei Fang
- Xiao-Jun WuXWXiao-Jun Wu
- 17 January 2025
- journal article
- research article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 310
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
This publication has 20 references indexed in Scilit:
- Context-Based and Diversity-Driven Specificity in Compositional Zero-Shot Learning2024
- CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning2023
- Learning to Prompt for Continual Learning2022
- Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning2022
- DER: Dynamically Expandable Representation for Class Incremental Learning2021
- A comprehensive study of class incremental learning algorithms for visual tasksNeural Networks, 2021
- Large Scale Incremental Learning2019
- Continual lifelong learning with neural networks: A reviewNeural Networks, 2019
- iCaRL: Incremental Classifier and Representation Learning2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017