# Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks

arXiv: https://arxiv.org/abs/2310.09436 · HTML: https://mlsanity.com/paper/2310.09436/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 65 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## Builds on (most cited first, 30 of 51)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [The Lottery Ticket Hypothesis for Pre-trained BERT Networks](https://mlsanity.com/paper/2007.12223/) (2020)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Continual Pre-training of Language Models](https://mlsanity.com/paper/2302.03241/) (2023)
- [Episodic Memory in Lifelong Language Learning](https://mlsanity.com/paper/1906.01076/) (2019)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [An Empirical Investigation of the Role of Pre-training in Lifelong Learning](https://mlsanity.com/paper/2112.09153/) (2021)
- [On the Effect of Dropping Layers of Pre-trained Transformer Models](https://mlsanity.com/paper/2004.03844/) (2020)
- [LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5](https://mlsanity.com/paper/2110.07298/) (2021)
- [Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning](https://mlsanity.com/paper/2112.02706/) (2021)
- [Continual Learning for Text Classification with Information Disentanglement Based Regularization](https://mlsanity.com/paper/2104.05489/) (2021)
- [Continual Learning in Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2012.15504/) (2020)

## Built on by (most cited first, 7 of 7)

- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Disentangling and Mitigating the Impact of Task Similarity for Continual Learning](https://mlsanity.com/paper/2405.20236/) (2024)
- [Recurrent Knowledge Identification and Fusion for Language Model Continual Learning](https://mlsanity.com/paper/2502.17510/) (2025)
- [MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning](https://mlsanity.com/paper/2407.20999/) (2024)
- [Optimal Task Order for Continual Learning of Multiple Tasks](https://mlsanity.com/paper/2502.03350/) (2025)
- [FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning](https://mlsanity.com/paper/2601.03938/) (2026)
- [AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning](https://mlsanity.com/paper/2509.17348/) (2025)

## Abstract (arXiv)

Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcoming CF. Some work has also been done on KT when the tasks are similar. To our knowledge, only one method has been proposed to learn a sequence of mixed tasks. However, these techniques still suffer from CF and/or limited KT. This paper proposes a new CL method to achieve both. It overcomes CF by isolating the knowledge of each task via discovering a subnetwork for it. A soft-masking mechanism is also proposed to preserve the previous knowledge and to enable the new task to leverage the past knowledge to achieve KT. Experiments using classification, generation, information extraction, and their mixture (i.e., heterogeneous tasks) show that the proposed method consistently outperforms strong baselines.