Randomized Neural Network with Adaptive Forward Regularization for Online Task-free Class Incremental Learning

TL;DR

This paper introduces a novel randomized neural network framework with adaptive regularization for online task-free class incremental learning, effectively reducing forgetting and improving learning in non-i.i.d. streaming scenarios.

Contribution

It proposes a new randomized neural network approach with adaptive forward regularization, including a Bayesian extension, to enhance online class incremental learning without replay.

Findings

Outperforms canonical ridge style in OTCIL scenarios

Effectively avoids catastrophic forgetting in long task streams

Demonstrates superior performance on image datasets with multiple metrics

Abstract

Class incremental learning (CIL) requires an agent to learn distinct tasks consecutively with knowledge retention against forgetting. Problems impeding the practical applications of CIL methods are twofold: (1) non-i.i.d batch streams and no boundary prompts to update, known as the harsher online task-free CIL (OTCIL) scenario; (2) CIL methods suffer from memory loss in learning long task streams, as shown in Fig. 1 (a). To achieve efficient decision-making and decrease cumulative regrets during the OTCIL process, a randomized neural network (Randomized NN) with forward regularization (-F) is proposed to resist forgetting and enhance learning performance. This general framework integrates unsupervised knowledge into recursive convex optimization, has no learning dissipation, and can outperform the canonical ridge style (-R) in OTCIL. Based on this framework, we derive the algorithm of the ensemble deep random vector functional link network (edRVFL) with adjustable forward regularization (-kF), where k mediates the intensity of the intervention. edRVFL-kF generates one-pass closed-form incremental updates and variable learning rates, effectively avoiding past replay and catastrophic forgetting while achieving superior performance. Moreover, to curb unstable penalties caused by non-i.i.d and mitigate intractable tuning of -kF in OTCIL, we improve it to the plug-and-play edRVFL-kF-Bayes, enabling all hard ks in multiple sub-learners to be self-adaptively determined based on Bayesian learning. Experiments were conducted on 2 image datasets including 6 metrics, dynamic performance, ablation tests, and compatibility, which distinctly validates the efficacy of our OTCIL frameworks with -kF-Bayes and -kF styles.