On Understanding of the Dynamics of Model Capacity in Continual Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chakraborty, Supriyo, Raghavan, Krishnan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912536983502848
author Chakraborty, Supriyo
Raghavan, Krishnan
author_facet Chakraborty, Supriyo
Raghavan, Krishnan
contents The stability-plasticity dilemma, closely related to a neural network's (NN) capacity-its ability to represent tasks-is a fundamental challenge in continual learning (CL). Within this context, we introduce CL's effective model capacity (CLEMC) that characterizes the dynamic behavior of the stability-plasticity balance point. We develop a difference equation to model the evolution of the interplay between the NN, task data, and optimization procedure. We then leverage CLEMC to demonstrate that the effective capacity-and, by extension, the stability-plasticity balance point is inherently non-stationary. We show that regardless of the NN architecture or optimization method, a NN's ability to represent new tasks diminishes when incoming task distributions differ from previous ones. We conduct extensive experiments to support our theoretical findings, spanning a range of architectures-from small feedforward network and convolutional networks to medium-sized graph neural networks and transformer-based large language models with millions of parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08052
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On Understanding of the Dynamics of Model Capacity in Continual Learning
Chakraborty, Supriyo
Raghavan, Krishnan
Machine Learning
Artificial Intelligence
The stability-plasticity dilemma, closely related to a neural network's (NN) capacity-its ability to represent tasks-is a fundamental challenge in continual learning (CL). Within this context, we introduce CL's effective model capacity (CLEMC) that characterizes the dynamic behavior of the stability-plasticity balance point. We develop a difference equation to model the evolution of the interplay between the NN, task data, and optimization procedure. We then leverage CLEMC to demonstrate that the effective capacity-and, by extension, the stability-plasticity balance point is inherently non-stationary. We show that regardless of the NN architecture or optimization method, a NN's ability to represent new tasks diminishes when incoming task distributions differ from previous ones. We conduct extensive experiments to support our theoretical findings, spanning a range of architectures-from small feedforward network and convolutional networks to medium-sized graph neural networks and transformer-based large language models with millions of parameters.
title On Understanding of the Dynamics of Model Capacity in Continual Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.08052