# Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations

arXiv: https://arxiv.org/abs/2203.06514 · HTML: https://mlsanity.com/paper/2203.06514/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 12 Mar 2022.

## Builds on (most cited first, 30 of 34)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [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)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Orthogonal Gradient Descent for Continual Learning](https://mlsanity.com/paper/1910.07104/) (2019)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Supermasks in Superposition](https://mlsanity.com/paper/2006.14769/) (2020)
- [k-Sparse Autoencoders](https://mlsanity.com/paper/1312.5663/) (2013)
- [Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics](https://mlsanity.com/paper/2007.07400/) (2020)
- [Towards Robust Evaluations of Continual Learning](https://mlsanity.com/paper/1805.09733/) (2018)
- [Training Networks in Null Space of Feature Covariance for Continual Learning](https://mlsanity.com/paper/2103.07113/) (2021)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization](https://mlsanity.com/paper/1802.01569/) (2018)
- [Continual Learning in Low-rank Orthogonal Subspaces](https://mlsanity.com/paper/2010.11635/) (2020)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning](https://mlsanity.com/paper/2009.01797/) (2020)
- [TRGP: Trust Region Gradient Projection for Continual Learning](https://mlsanity.com/paper/2202.02931/) (2022)
- [Sparse DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1810.09619/) (2018)
- [Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning](https://mlsanity.com/paper/2110.04593/) (2021)
- [Powerpropagation: A sparsity inducing weight reparameterisation](https://mlsanity.com/paper/2110.00296/) (2021)
- [How Can We Be So Dense? The Benefits of Using Highly Sparse Representations](https://mlsanity.com/paper/1903.11257/) (2019)
- [Selfless Sequential Learning](https://mlsanity.com/paper/1806.05421/) (2018)

## Built on by (most cited first, 19 of 19)

- [Sparse Coding in a Dual Memory System for Lifelong Learning](https://mlsanity.com/paper/2301.05058/) (2022)
- [Continual Learning in the Frequency Domain](https://mlsanity.com/paper/2410.06645/) (2024)
- [Sparse Distributed Memory is a Continual Learner](https://mlsanity.com/paper/2303.11934/) (2023)
- [Elephant Neural Networks: Born to Be a Continual Learner](https://mlsanity.com/paper/2310.01365/) (2023)
- [Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters](https://mlsanity.com/paper/2311.18763/) (2023)
- [MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs](https://mlsanity.com/paper/2506.07899/) (2025)
- [BrainWash: A Poisoning Attack to Forget in Continual Learning](https://mlsanity.com/paper/2311.11995/) (2023)
- [TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion](https://mlsanity.com/paper/2310.08217/) (2023)
- [A Meta-learning based Generalizable Indoor Localization Model using Channel State Information](https://mlsanity.com/paper/2305.13453/) (2023)
- [CovarNav: Machine Unlearning via Model Inversion and Covariance Navigation](https://mlsanity.com/paper/2311.12999/) (2023)
- [A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning](https://mlsanity.com/paper/2304.06738/) (2023)
- [Dynamically Modular and Sparse General Continual Learning](https://mlsanity.com/paper/2301.00620/) (2023)
- [Towards guarantees for parameter isolation in continual learning](https://mlsanity.com/paper/2310.01165/) (2023)
- [Continual Learning Beyond Experience Rehearsal and Full Model Surrogates](https://mlsanity.com/paper/2505.21942/) (2025)
- [Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions](https://mlsanity.com/paper/2509.19159/) (2025)
- [Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2601.21341/) (2026)
- [Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2601.21345/) (2026)
- [Replay in the Silent Degrees of Freedom: Continual Learning Without an Offline Phase](https://mlsanity.com/paper/2609.31630/) (2026)
- [A Tropical Geometry View of Forgetting: A Per-Unit Projector for Knowledge-Preserving Fine-Tuning](https://mlsanity.com/paper/2610.04670/) (2026)

## Abstract (arXiv)

Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously learned information upon learning new ones. This phenomenon is called "catastrophic forgetting" and is deeply rooted in the stability-plasticity dilemma. Overcoming catastrophic forgetting in deep neural networks has become an active field of research in recent years. In particular, gradient projection-based methods have recently shown exceptional performance at overcoming catastrophic forgetting. This paper proposes two biologically-inspired mechanisms based on sparsity and heterogeneous dropout that significantly increase a continual learner's performance over a long sequence of tasks. Our proposed approach builds on the Gradient Projection Memory (GPM) framework. We leverage k-winner activations in each layer of a neural network to enforce layer-wise sparse activations for each task, together with a between-task heterogeneous dropout that encourages the network to use non-overlapping activation patterns between different tasks. In addition, we introduce two new benchmarks for continual learning under distributional shift, namely Continual Swiss Roll and ImageNet SuperDog-40. Lastly, we provide an in-depth analysis of our proposed method and demonstrate a significant performance boost on various benchmark continual learning problems.