paper-with-me

Papers

Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking

2023-11-17 · Hong Liu, Yucheng Cai, Yuan Zhou, Zhijian Ou, Yi Huang, Junlan Feng

Continual learning is crucial for dialog state tracking (DST) in dialog systems, since requirements from users for new functionalities are often encountered. However, most of existing continual learning methods for DST require task identities during testing, which is a severe limit in real-world applications. In this paper, we aim to address continual learning of DST in the class-incremental scenario (namely the task identity is unknown in testing). Inspired by the recently emerging prompt tuning method that performs well on dialog systems, we propose to use the prompt pool method, where we maintain a pool of key-value paired prompts and select prompts from the pool according to the distance between the dialog history and the prompt keys. The proposed method can automatically identify tasks and select appropriate prompts during testing. We conduct experiments on Schema-Guided Dialog dataset (SGD) and another dataset collected from a real-world dialog application. Experiment results show that the prompt pool method achieves much higher joint goal accuracy than the baseline. After combining with a rehearsal buffer, the model performance can be further improved.

📄 PDF Abstract BibTeX arXiv:2311.10271

Code (1)

thu-spmi/ppt2dst 공식 구현 jax

Tasks

Continual Learningdialog state tracking

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

Similar Papers 제목 키워드 기반

Prompt Customization for Continual Learning

2024-04-28 · Yong Dai, Xiaopeng Hong, Yabin Wang, Zhiheng Ma 외

Contemporary continual learning approaches typically select prompts from a pool, which function as supplementary inputs to a pre-trained model. However, this strategy is hindered by the inherent noise of its selection ap…

Continual LearningIncremental Learning

One-stage Prompt-based Continual Learning

2024-02-25 · Youngeun Kim, Yuhang Li, Priyadarshini Panda

Prompt-based Continual Learning (PCL) has gained considerable attention as a promising continual learning solution as it achieves state-of-the-art performance while preventing privacy violation and memory overhead issues…

Continual Learning

UniPrompt-CL: Sustainable Continual Learning in Medical AI with Unified Prompt Pools

2025-08-14 · Gyutae Oh, Jitae Shin arxiv

Modern AI models are typically trained on static datasets, limiting their ability to continuously adapt to rapidly evolving real-world environments. While continual learning (CL) addresses this limitation, most CL method…

Incremental LearningContinual Learning

Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection

2026-03-02 · Yaoteng Zhang, Zhou Qing, Junyu Gao, Qi Wang arxiv

Incremental Object Detection (IOD) aims to continuously learn new object categories without forgetting previously learned ones. Recently, prompt-based methods have gained popularity for their replay-free design and param…

General KnowledgeObject Detection

PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer

2024-07-04 · Qian Feng, Hanbin Zhao, Chao Zhang, Jiahua Dong 외

Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent…

Incremental Learning