paper-with-me

Papers

Continual Learning with Dirichlet Generative-based Rehearsal

2023-09-13 · Min Zeng, Wei Xue, Qifeng Liu, Yike Guo

Recent advancements in data-driven task-oriented dialogue systems (ToDs) struggle with incremental learning due to computational constraints and time-consuming issues. Continual Learning (CL) attempts to solve this by avoiding intensive pre-training, but it faces the problem of catastrophic forgetting (CF). While generative-based rehearsal CL methods have made significant strides, generating pseudo samples that accurately reflect the underlying task-specific distribution is still a challenge. In this paper, we present Dirichlet Continual Learning (DCL), a novel generative-based rehearsal strategy for CL. Unlike the traditionally used Gaussian latent variable in the Conditional Variational Autoencoder (CVAE), DCL leverages the flexibility and versatility of the Dirichlet distribution to model the latent prior variable. This enables it to efficiently capture sentence-level features of previous tasks and effectively guide the generation of pseudo samples. In addition, we introduce Jensen-Shannon Knowledge Distillation (JSKD), a robust logit-based knowledge distillation method that enhances knowledge transfer during pseudo sample generation. Our experiments confirm the efficacy of our approach in both intent detection and slot-filling tasks, outperforming state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2309.06917

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningIncremental LearningIntent DetectionKnowledge DistillationSentenceslot-fillingSlot FillingTask-Oriented Dialogue SystemsTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Logarithmic Continual Learning

2022-01-17 · Wojciech Masarczyk, Paweł Wawrzyński, Daniel Marczak, Kamil Deja 외

We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual learning (CL), training samples come in s…

Continual Learning

Joint Diffusion models in Continual Learning

2024-11-12 · Paweł Skierś, Kamil Deja

In this work, we introduce JDCL - a new method for continual learning with generative rehearsal based on joint diffusion models. Neural networks suffer from catastrophic forgetting defined as abrupt loss in the model's p…

Continual LearningKnowledge Distillation

GUIDE: Guidance-based Incremental Learning with Diffusion Models

2024-03-06 · Bartosz Cywiński, Kamil Deja, Tomasz Trzciński, Bartłomiej Twardowski 외

We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling reh…

Continual LearningIncremental Learning

A Closer Look at Rehearsal-Free Continual Learning

2022-03-31 · James Seale Smith, Junjiao Tian, Shaunak Halbe, Yen-Chang Hsu 외

Continual learning is a setting where machine learning models learn novel concepts from continuously shifting training data, while simultaneously avoiding degradation of knowledge on previously seen classes which may dis…

Continual LearningKnowledge DistillationL2 RegularizationNovel Concepts

Understanding the Role of Rehearsal Scale in Continual Learning under Varying Model Capacities

2026-02-24 · JinLi He, Liang Bai, Xian Yang arxiv

Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of…

Continual Learning