# Efficient Architecture Search for Continual Learning

arXiv: https://arxiv.org/abs/2006.04027 · HTML: https://mlsanity.com/paper/2006.04027/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2020.

## Built on by (most cited first, 30 of 34)

- [RMM: Reinforced Memory Management for Class-Incremental Learning](https://mlsanity.com/paper/2301.05792/) (2023)
- [Efficient Feature Transformations for Discriminative and Generative Continual Learning](https://mlsanity.com/paper/2103.13558/) (2021)
- [Architecture Matters in Continual Learning](https://mlsanity.com/paper/2202.00275/) (2022)
- [Recent Advances of Multimodal Continual Learning: A Comprehensive Survey](https://mlsanity.com/paper/2410.05352/) (2024)
- [Prototype-Guided Memory Replay for Continual Learning](https://mlsanity.com/paper/2108.12641/) (2021)
- [Discrete Key-Value Bottleneck](https://mlsanity.com/paper/2207.11240/) (2022)
- [Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning](https://mlsanity.com/paper/2308.02346/) (2023)
- [Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks](https://mlsanity.com/paper/2308.04749/) (2023)
- [AdaXpert: Adapting Neural Architecture for Growing Data](https://mlsanity.com/paper/2107.00254/) (2021)
- [Continual Learning for Smart City: A Survey](https://mlsanity.com/paper/2404.00983/) (2024)
- [Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networks](https://mlsanity.com/paper/2309.09550/) (2023)
- [Multi-View Class Incremental Learning](https://mlsanity.com/paper/2306.09675/) (2023)
- [Deep progressive reinforcement learning-based flexible resource scheduling framework for IRS and UAV-assisted MEC system](https://mlsanity.com/paper/2408.01248/) (2024)
- [Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning](https://mlsanity.com/paper/2411.15469/) (2024)
- [Tuned Compositional Feature Replays for Efficient Stream Learning](https://mlsanity.com/paper/2104.02206/) (2021)
- [Exploring the Intersection between Neural Architecture Search and Continual Learning](https://mlsanity.com/paper/2206.05625/) (2022)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [Effects of Architectures on Continual Semantic Segmentation](https://mlsanity.com/paper/2302.10718/) (2023)
- [IF2Net: Innately Forgetting-Free Networks for Continual Learning](https://mlsanity.com/paper/2306.10480/) (2023)
- [Efficient Expansion and Gradient Based Task Inference for Replay Free Incremental Learning](https://mlsanity.com/paper/2312.01188/) (2023)
- [Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence](https://mlsanity.com/paper/2101.09225/) (2021)
- [HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning](https://mlsanity.com/paper/2309.15038/) (2023)
- [Overcoming Domain Drift in Online Continual Learning](https://mlsanity.com/paper/2405.09133/) (2024)
- [What Can AutoML Do For Continual Learning?](https://mlsanity.com/paper/2311.11963/) (2023)
- [Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning](https://mlsanity.com/paper/2408.14976/) (2024)
- [Similarity-based context aware continual learning for spiking neural networks](https://mlsanity.com/paper/2411.05802/) (2024)
- [SEAL: Searching Expandable Architectures for Incremental Learning](https://mlsanity.com/paper/2505.10457/) (2025)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [Optimizing Connectivity through Network Gradients for Restricted Boltzmann Machines](https://mlsanity.com/paper/2209.06932/) (2022)
- [UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization](https://mlsanity.com/paper/2507.04706/) (2025)

## Abstract (arXiv)

Continual learning with neural networks is an important learning framework in AI that aims to learn a sequence of tasks well. However, it is often confronted with three challenges: (1) overcome the catastrophic forgetting problem, (2) adapt the current network to new tasks, and meanwhile (3) control its model complexity. To reach these goals, we propose a novel approach named as Continual Learning with Efficient Architecture Search, or CLEAS in short. CLEAS works closely with neural architecture search (NAS) which leverages reinforcement learning techniques to search for the best neural architecture that fits a new task. In particular, we design a neuron-level NAS controller that decides which old neurons from previous tasks should be reused (knowledge transfer), and which new neurons should be added (to learn new knowledge). Such a fine-grained controller allows one to find a very concise architecture that can fit each new task well. Meanwhile, since we do not alter the weights of the reused neurons, we perfectly memorize the knowledge learned from previous tasks. We evaluate CLEAS on numerous sequential classification tasks, and the results demonstrate that CLEAS outperforms other state-of-the-art alternative methods, achieving higher classification accuracy while using simpler neural architectures.