Saved in:
Bibliographic Details
Main Authors: Li, Ruilin, Zou, Heming, Yan, Xiufeng, Liang, Zheming, Yang, Jie, Li, Chenliang, Yang, Xue
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.19145
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910060236505088
author Li, Ruilin
Zou, Heming
Yan, Xiufeng
Liang, Zheming
Yang, Jie
Li, Chenliang
Yang, Xue
author_facet Li, Ruilin
Zou, Heming
Yan, Xiufeng
Liang, Zheming
Yang, Jie
Li, Chenliang
Yang, Xue
contents Recent paradigms in Random Projection Layer (RPL)-based continual representation learning have demonstrated superior performance when building upon a pre-trained model (PTM). These methods insert a randomly initialized RPL after a PTM to enhance feature representation in the initial stage. Subsequently, a linear classification head is used for analytic updates in the continual learning stage. However, under severe domain gaps between pre-trained representations and target domains, a randomly initialized RPL exhibits limited expressivity under large domain shifts. While largely scaling up the RPL dimension can improve expressivity, it also induces an ill-conditioned feature matrix, thereby destabilizing the recursive analytic updates of the linear head. To this end, we propose the Stochastic Continual Learner with MemoryGuard Supervisory Mechanism (SCL-MGSM). Unlike random initialization, MGSM constructs the projection layer via a principled, data-guided mechanism that progressively selects target-aligned random bases to adapt the PTM representation to downstream tasks. This facilitates the construction of a compact yet expressive RPL while improving the numerical stability of analytic updates. Extensive experiments on multiple exemplar-free Class Incremental Learning (CIL) benchmarks demonstrate that SCL-MGSM achieves superior performance compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19145
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
Li, Ruilin
Zou, Heming
Yan, Xiufeng
Liang, Zheming
Yang, Jie
Li, Chenliang
Yang, Xue
Machine Learning
Recent paradigms in Random Projection Layer (RPL)-based continual representation learning have demonstrated superior performance when building upon a pre-trained model (PTM). These methods insert a randomly initialized RPL after a PTM to enhance feature representation in the initial stage. Subsequently, a linear classification head is used for analytic updates in the continual learning stage. However, under severe domain gaps between pre-trained representations and target domains, a randomly initialized RPL exhibits limited expressivity under large domain shifts. While largely scaling up the RPL dimension can improve expressivity, it also induces an ill-conditioned feature matrix, thereby destabilizing the recursive analytic updates of the linear head. To this end, we propose the Stochastic Continual Learner with MemoryGuard Supervisory Mechanism (SCL-MGSM). Unlike random initialization, MGSM constructs the projection layer via a principled, data-guided mechanism that progressively selects target-aligned random bases to adapt the PTM representation to downstream tasks. This facilitates the construction of a compact yet expressive RPL while improving the numerical stability of analytic updates. Extensive experiments on multiple exemplar-free Class Incremental Learning (CIL) benchmarks demonstrate that SCL-MGSM achieves superior performance compared to state-of-the-art methods.
title Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
topic Machine Learning
url https://arxiv.org/abs/2603.19145