# Neural Architecture Search for Class-incremental Learning

arXiv: https://arxiv.org/abs/1909.06686 · HTML: https://mlsanity.com/paper/1909.06686/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal](https://mlsanity.com/paper/2403.01244/) (2024)
- [RMM: Reinforced Memory Management for Class-Incremental Learning](https://mlsanity.com/paper/2301.05792/) (2023)
- [Class-Incremental Exemplar Compression for Class-Incremental Learning](https://mlsanity.com/paper/2303.14042/) (2023)
- [Architecture Matters in Continual Learning](https://mlsanity.com/paper/2202.00275/) (2022)
- [Exploring the Intersection between Neural Architecture Search and Continual Learning](https://mlsanity.com/paper/2206.05625/) (2022)
- [SEE: Continual Fine-tuning with Sequential Ensemble of Experts](https://mlsanity.com/paper/2504.06664/) (2025)
- [Incremental Learning with Differentiable Architecture and Forgetting Search](https://mlsanity.com/paper/2205.09875/) (2022)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning](https://mlsanity.com/paper/2311.18630/) (2023)
- [HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search](https://mlsanity.com/paper/2605.04103/) (2026)

## Abstract (arXiv)

In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity saturation because a neural network's ability to generalize to new concepts is limited by its fixed capacity. To understand how to expand a continual learner, we focus on the neural architecture design problem in the context of class-incremental learning: at each time step, the learner must optimize its performance on all classes observed so far by selecting the most competitive neural architecture. To tackle this problem, we propose Continual Neural Architecture Search (CNAS): an autoML approach that takes advantage of the sequential nature of class-incremental learning to efficiently and adaptively identify strong architectures in a continual learning setting. We employ a task network to perform the classification task and a reinforcement learning agent as the meta-controller for architecture search. In addition, we apply network transformations to transfer weights from previous learning step and to reduce the size of the architecture search space, thus saving a large amount of computational resources. We evaluate CNAS on the CIFAR-100 dataset under varied incremental learning scenarios with limited computational power (1 GPU). Experimental results demonstrate that CNAS outperforms architectures that are optimized for the entire dataset. In addition, CNAS is at least an order of magnitude more efficient than naively using existing autoML methods.