# Reminding the Incremental Language Model via Data-Free Self-Distillation

arXiv: https://arxiv.org/abs/2110.08745 · HTML: https://mlsanity.com/paper/2110.08745/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for continual learning, one of 12 directions in Knowledge distillation.
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 17 Oct 2021.

## Placed in

- Knowledge distillation / [Distillation for continual learning](https://mlsanity.com/distill/distillation-for-continual-learning/)

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [Episodic Memory in Lifelong Language Learning](https://mlsanity.com/paper/1906.01076/) (2019)
- [FearNet: Brain-Inspired Model for Incremental Learning](https://mlsanity.com/paper/1711.10563/) (2017)
- [LAMOL: LAnguage MOdeling for Lifelong Language Learning](https://mlsanity.com/paper/1909.03329/) (2019)
- [Learning to Generate Reviews and Discovering Sentiment](https://mlsanity.com/paper/1704.01444/) (2017)
- [Generative replay with feedback connections as a general strategy for continual learning](https://mlsanity.com/paper/1809.10635/) (2018)
- [Lifelong GAN: Continual Learning for Conditional Image Generation](https://mlsanity.com/paper/1907.10107/) (2019)
- [Efficient Meta Lifelong-Learning with Limited Memory](https://mlsanity.com/paper/2010.02500/) (2020)
- [Continual Learning for Recurrent Neural Networks: an Empirical Evaluation](https://mlsanity.com/paper/2103.07492/) (2021)
- [Lifelong Language Knowledge Distillation](https://mlsanity.com/paper/2010.02123/) (2020)
- [BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance](https://mlsanity.com/paper/2010.06133/) (2020)
- [Crossmodal Language Grounding in an Embodied Neurocognitive Model](https://mlsanity.com/paper/2006.13546/) (2020)

## Built on by (most cited first, 3 of 3)

- [RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning](https://mlsanity.com/paper/2205.10857/) (2022)
- [TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models](https://mlsanity.com/paper/2603.24518/) (2026)
- [Ask Question First for Enhancing Lifelong Language Learning](https://mlsanity.com/paper/2208.08367/) (2022)

## Abstract (arXiv)

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance dramatically decreases when fewer pseudo-data are employed. In addition, the distribution of pseudo-data gradually deviates from the real data with the sequential learning of different tasks. The deviation will be greater with more tasks learned, which results in more serious catastrophic forgetting. To address these issues, we propose reminding incremental language model via data-free self-distillation (DFSD), which includes self-distillation based on the Earth Mover's Distance and hidden data augmentation. By estimating the knowledge distribution in all layers of GPT-2 and transforming it from teacher model to student model, the Self-distillation based on the Earth Mover's Distance can significantly reduce the demand for pseudo-data. Hidden data augmentation can greatly alleviate the catastrophic forgetting caused by deviations via modeling the generation of pseudo-data as a hidden data augmentation process, where each sample is a mixture of all trained task data. The experimental results demonstrate that our DFSD can exceed the previous state-of-the-art methods even if the maximum decrease in pseudo-data is 90%.