# Structural features of the fly olfactory circuit mitigate the stability-plasticity dilemma in continual learning

arXiv: https://arxiv.org/abs/2502.01427 · HTML: https://mlsanity.com/paper/2502.01427/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2025.

## Built on by (most cited first, 14 of 14)

- [FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts](https://mlsanity.com/paper/2510.08396/) (2025)
- [Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning](https://mlsanity.com/paper/2510.16882/) (2025)
- [Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning](https://mlsanity.com/paper/2510.16877/) (2025)
- [TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.11119/) (2026)
- [NeuroLoRA: Context-Aware Neuromodulation for Parameter-Efficient Multi-Task Adaptation](https://mlsanity.com/paper/2603.12378/) (2026)
- [Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection](https://mlsanity.com/paper/2603.19145/) (2026)
- [FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts](https://mlsanity.com/paper/2607.00162/) (2026)
- [Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2511.02567/) (2025)
- [Representation Collapse in Sequential Post-Training of Large Language Models](https://mlsanity.com/paper/2605.30524/) (2026)
- [The Long-Term Effects of Data Selection in LLM Fine-Tuning](https://mlsanity.com/paper/2605.30537/) (2026)
- [Gains: Fine-grained Federated Domain Adaptation in Open Set](https://mlsanity.com/paper/2510.15967/) (2025)
- [CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies](https://mlsanity.com/paper/2602.15367/) (2026)
- [SPARCL: Spectral Partitioned Analytic Continual Learning](https://mlsanity.com/paper/2608.21307/) (2026)
- [Score the Update, Not the Token: Descent-Aligned Routing for Combinatorial LoRA Experts](https://mlsanity.com/paper/2610.00493/) (2026)

## Abstract (arXiv)

Artificial neural networks face the stability-plasticity dilemma in continual learning, while the brain can maintain memories and remain adaptable. However, the biological strategies for continual learning and their potential to inspire learning algorithms in neural networks are poorly understood. This study presents a minimal model of the fly olfactory circuit to investigate the biological strategies that support continual odor learning. We introduce the fly olfactory circuit as a plug-and-play component, termed the Fly Model, which can integrate with modern machine learning methods to address this dilemma. Our findings demonstrate that the Fly Model enhances both memory stability and learning plasticity, overcoming the limitations of current continual learning strategies. We validated its effectiveness across various challenging continual learning scenarios using commonly used datasets. The fly olfactory system serves as an elegant biological circuit for lifelong learning, offering a module that enhances continual learning with minimal additional computational cost for machine learning.