受果蝇嗅觉系统启发，提升预训练模型持续学习效率
Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
- 借鉴果蝇嗅觉电路设计，缓解特征共线性问题
- 训练时间显著降低，性能媲美或超越当前最优方法
- 适合对实时性要求高的持续学习场景
采用几乎冻结的预训练模型，持续表示学习将参数更新重构为相似性匹配问题，以缓解灾难性遗忘。然而，直接利用预训练特征进行下游任务时，相似性匹配阶段常面临多重共线性问题，而更先进的方法在实时、低延迟应用中计算开销过大。受果蝇嗅觉回路启发，本文提出Fly-CL——一种兼容多种预训练主干网络的生物启发框架。该方法显著缩短训练时间，同时性能达到或超过现有最先进水平。理论分析表明，Fly-CL逐步解决共线性问题，实现高效相似性匹配且时间复杂度低。跨多种网络架构和数据设置的大量仿真实验验证了其有效性。代码已开源：https://github.com/gfyddha/Fly-CL。
原文摘要 · Abstract (English)
Using a nearly-frozen pretrained model, the continual representation learning paradigm reframes parameter updates as a similarity-matching problem to mitigate catastrophic forgetting. However, directly leveraging pretrained features for downstream tasks often suffers from multicollinearity in the similarity-matching stage, and more advanced methods can be computationally prohibitive for real-time, low-latency applications. Inspired by the fly olfactory circuit, we propose Fly-CL, a bio-inspired framework compatible with a wide range of pretrained backbones. Fly-CL substantially reduces training time while achieving performance comparable to or exceeding that of current state-of-the-art methods. We theoretically show how Fly-CL progressively resolves multicollinearity, enabling more effective similarity matching with low time complexity. Extensive simulation experiments across diverse network architectures and data regimes validate Fly-CL's effectiveness in addressing this challenge through a biologically inspired design. Code is available at https://github.com/gfyddha/Fly-CL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。