paper-with-me

Papers

Vector Quantization Prompting for Continual Learning

2024-10-27 · Li Jiao, Qiuxia Lai, Yu Li, Qiang Xu

Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i.e., prompts) to encode task knowledge, from which appropriate ones are selected to guide the fixed pre-trained model in generating features tailored to a certain task. However, existing methods rely on predicting prompt identities for prompt selection, where the identity prediction process cannot be optimized with task loss. This limitation leads to sub-optimal prompt selection and inadequate adaptation of pre-trained features for a specific task. Previous efforts have tried to address this by directly generating prompts from input queries instead of selecting from a set of candidates. However, these prompts are continuous, which lack sufficient abstraction for task knowledge representation, making them less effective for continual learning. To address these challenges, we propose VQ-Prompt, a prompt-based continual learning method that incorporates Vector Quantization (VQ) into end-to-end training of a set of discrete prompts. In this way, VQ-Prompt can optimize the prompt selection process with task loss and meanwhile achieve effective abstraction of task knowledge for continual learning. Extensive experiments show that VQ-Prompt outperforms state-of-the-art continual learning methods across a variety of benchmarks under the challenging class-incremental setting. The code is available at \href{https://github.com/jiaolifengmi/VQ-Prompt}{this https URL}.

📄 PDF Abstract BibTeX arXiv:2410.20444

Code (1)

jiaolifengmi/vq-prompt 공식 구현 pytorch

Tasks

Continual LearningQuantization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces

2024-10-21 · Jifeng Hu, Sili Huang, Li Shen, Zhejian Yang 외

Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. However, most research only focuses on limite…

Continual LearningLifelong learningOffline RLQuantization

Point Cloud Quantization through Multimodal Prompting for 3D Understanding

2025-11-15 · Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu 외 arxiv

Vector quantization has emerged as a powerful tool in large-scale multimodal models, unifying heterogeneous representations through discrete token encoding. However, its effectiveness hinges on robust codebook design. Cu…

Generalized residual vector quantization for large scale data

2016-09-17 · Liu Shicong, Shao Junru, Lu Hongtao

Vector quantization is an essential tool for tasks involving large scale data, for example, large scale similarity search, which is crucial for content-based information retrieval and analysis. In this paper, we propose …

Information RetrievalQuantizationRetrieval

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models

2025-12-22 · Michael S. Zhang, Rishi A. Ruia, Arnav Kewalram, Saathvik Dharmapuram 외 arxiv

Catastrophic forgetting poses a fundamental challenge in continual learning, particularly when models are quantized for deployment efficiency. We systematically investigate the interplay between quantization precision (F…

Computational EfficiencyContinual LearningCode Generation

QuantEase: Optimization-based Quantization for Language Models

2023-09-05 · Kayhan Behdin, Ayan Acharya, Aman Gupta, Qingquan Song 외

With the rising popularity of Large Language Models (LLMs), there has been an increasing interest in compression techniques that enable their efficient deployment. This study focuses on the Post-Training Quantization (PT…

GPUQuantization