# Deep Generative Dual Memory Network for Continual Learning

arXiv: https://arxiv.org/abs/1710.10368 · HTML: https://mlsanity.com/paper/1710.10368/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2017.

## Built on by (most cited first, 30 of 59)

- [CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2211.13218/) (2022)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA](https://mlsanity.com/paper/2304.06027/) (2023)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Distilling Causal Effect of Data in Class-Incremental Learning](https://mlsanity.com/paper/2103.01737/) (2021)
- [Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System](https://mlsanity.com/paper/2201.12604/) (2022)
- [Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning](https://mlsanity.com/paper/2112.02706/) (2021)
- [RECALL: Replay-based Continual Learning in Semantic Segmentation](https://mlsanity.com/paper/2108.03673/) (2021)
- [Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks](https://mlsanity.com/paper/2112.10017/) (2021)
- [A Theoretical Study on Solving Continual Learning](https://mlsanity.com/paper/2211.02633/) (2022)
- [CLIP model is an Efficient Continual Learner](https://mlsanity.com/paper/2210.03114/) (2022)
- [A Closer Look at Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2203.17269/) (2022)
- [Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.03271/) (2021)
- [Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer](https://mlsanity.com/paper/2101.09536/) (2021)
- [CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks](https://mlsanity.com/paper/2112.02714/) (2021)
- [Learnability and Algorithm for Continual Learning](https://mlsanity.com/paper/2306.12646/) (2023)
- [A Multi-Head Model for Continual Learning via Out-of-Distribution Replay](https://mlsanity.com/paper/2208.09734/) (2022)
- [An Investigation of Replay-based Approaches for Continual Learning](https://mlsanity.com/paper/2108.06758/) (2021)
- [CRIL: Continual Robot Imitation Learning via Generative and Prediction Model](https://mlsanity.com/paper/2106.09422/) (2021)
- [Continual Learning Based on OOD Detection and Task Masking](https://mlsanity.com/paper/2203.09450/) (2022)
- [ConStruct-VL: Data-Free Continual Structured VL Concepts Learning](https://mlsanity.com/paper/2211.09790/) (2022)
- [Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition](https://mlsanity.com/paper/2103.08637/) (2021)
- [When Video Classification Meets Incremental Classes](https://mlsanity.com/paper/2106.15827/) (2021)
- [Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning](https://mlsanity.com/paper/2308.02346/) (2023)
- [Encoders and Ensembles for Task-Free Continual Learning](https://mlsanity.com/paper/2105.13327/) (2021)
- [Label-Efficient Online Continual Object Detection in Streaming Video](https://mlsanity.com/paper/2206.00309/) (2022)
- [Rectification-based Knowledge Retention for Continual Learning](https://mlsanity.com/paper/2103.16597/) (2021)
- [Continual Learning with Knowledge Transfer for Sentiment Classification](https://mlsanity.com/paper/2112.10021/) (2021)
- [Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters](https://mlsanity.com/paper/2311.18763/) (2023)

## Abstract (arXiv)

Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data. In this work, we derive inspiration from human memory to develop an architecture capable of learning continuously from sequentially incoming tasks, while averting catastrophic forgetting. Specifically, our contributions are: (i) a dual memory architecture emulating the complementary learning systems (hippocampus and the neocortex) in the human brain, (ii) memory consolidation via generative replay of past experiences, (iii) demonstrating advantages of generative replay and dual memories via experiments, and (iv) improved performance retention on challenging tasks even for low capacity models. Our architecture displays many characteristics of the mammalian memory and provides insights on the connection between sleep and learning.