DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning

TL;DR

This paper introduces DLCFT, a continual learning method that fine-tunes pre-trained models using linearization and quadratic regularization, effectively preventing forgetting across various incremental learning scenarios.

Contribution

It proposes a novel linearization-based continual fine-tuning framework with quadratic regularization, improving performance and theoretical understanding of regularization methods in incremental learning.

Findings

Pre-trained models can be effectively fine-tuned continually with linearization techniques.

Quadratic regularization acts as an optimal policy for continual learning.

The method outperforms existing approaches in class-incremental tasks.

Abstract

Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore an alternative framework to incremental learning where we continually fine-tune the model from a pre-trained representation. Our method takes advantage of linearization technique of a pre-trained neural network for simple and effective continual learning. We show that this allows us to design a linear model where quadratic parameter regularization method is placed as the optimal continual learning policy, and at the same time enjoying the high performance of neural networks. We also show that the proposed algorithm enables parameter regularization methods to be applied to class-incremental problems. Additionally, we provide a theoretical reason why the existing parameter-space regularization algorithms such as EWC underperform on neural networks trained with cross-entropy loss. We show that the proposed method can prevent forgetting while achieving high continual fine-tuning performance on image classification tasks. To show that our method can be applied to general continual learning settings, we evaluate our method in data-incremental, task-incremental, and class-incremental learning problems.