Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zou, Heming, Zang, Yunliang, Xu, Wutong, Ji, Xiangyang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915826588712960
author Zou, Heming
Zang, Yunliang
Xu, Wutong
Ji, Xiangyang
author_facet Zou, Heming
Zang, Yunliang
Xu, Wutong
Ji, Xiangyang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16877
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
Zou, Heming
Zang, Yunliang
Xu, Wutong
Ji, Xiangyang
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.16877