# Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking

arXiv: https://arxiv.org/abs/2107.08173 · HTML: https://mlsanity.com/paper/2107.08173/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 17 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [Uncertainty-based Continual Learning with Adaptive Regularization](https://mlsanity.com/paper/1905.11614/) (2019)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [Global-to-local Memory Pointer Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1901.04713/) (2019)
- [Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog](https://mlsanity.com/paper/2004.11019/) (2020)
- [One Person, One Model, One World: Learning Continual User Representation without Forgetting](https://mlsanity.com/paper/2009.13724/) (2020)
- [Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems](https://mlsanity.com/paper/1905.05644/) (2019)
- [Conditional Generation and Snapshot Learning in Neural Dialogue Systems](https://mlsanity.com/paper/1606.03352/) (2016)
- [A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue](https://mlsanity.com/paper/1701.04024/) (2017)
- [Multi-level Memory for Task Oriented Dialogs](https://mlsanity.com/paper/1810.10647/) (2018)
- [Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification](https://mlsanity.com/paper/2106.11197/) (2021)

## Built on by (most cited first, 22 of 22)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Continual Learning of Natural Language Processing Tasks: A Survey](https://mlsanity.com/paper/2211.12701/) (2022)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Continual Prompt Tuning for Dialog State Tracking](https://mlsanity.com/paper/2203.06654/) (2022)
- [SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2505.02486/) (2025)
- [TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation](https://mlsanity.com/paper/2408.09857/) (2024)
- [Continual Learning Using a Kernel-Based Method Over Foundation Models](https://mlsanity.com/paper/2412.15571/) (2024)
- [Dynamic Dialogue Policy for Continual Reinforcement Learning](https://mlsanity.com/paper/2204.05928/) (2022)
- [Continual Learning for Generative AI: From LLMs to MLLMs and Beyond](https://mlsanity.com/paper/2506.13045/) (2025)
- [Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue](https://mlsanity.com/paper/2210.07783/) (2022)
- [Continual Dialogue State Tracking via Reason-of-Select Distillation](https://mlsanity.com/paper/2408.09846/) (2024)
- [Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting](https://mlsanity.com/paper/2506.09428/) (2025)
- [In-context Continual Learning Assisted by an External Continual Learner](https://mlsanity.com/paper/2412.15563/) (2024)
- [AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection](https://mlsanity.com/paper/2511.13880/) (2025)
- [Continual Learning Using Only Large Language Model Prompting](https://mlsanity.com/paper/2412.15479/) (2024)
- [Visually Grounded Continual Language Learning with Selective Specialization](https://mlsanity.com/paper/2310.15571/) (2023)
- [Self-Evolving LLMs via Continual Instruction Tuning](https://mlsanity.com/paper/2509.18133/) (2025)
- [Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking](https://mlsanity.com/paper/2311.10271/) (2023)
- [Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models](https://mlsanity.com/paper/2410.05802/) (2024)
- [Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?](https://mlsanity.com/paper/2212.10504/) (2022)
- [Overcoming Growth-Induced Forgetting in Task-Agnostic Continual Learning](https://mlsanity.com/paper/2408.10566/) (2024)

## Abstract (arXiv)

This ability to learn consecutive tasks without forgetting how to perform previously trained problems is essential for developing an online dialogue system. This paper proposes an effective continual learning for the task-oriented dialogue system with iterative network pruning, expanding and masking (TPEM), which preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks. Specifically, TPEM (i) leverages network pruning to keep the knowledge for old tasks, (ii) adopts network expanding to create free weights for new tasks, and (iii) introduces task-specific network masking to alleviate the negative impact of fixed weights of old tasks on new tasks. We conduct extensive experiments on seven different tasks from three benchmark datasets and show empirically that TPEM leads to significantly improved results over the strong competitors. For reproducibility, we submit the code and data at: https://github.com/siat-nlp/TPEM