Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mitchell, Rupert, Alliegro, Antonio, Camoriano, Raffaello, Carrión-Ojeda, Dustin, Carta, Antonio, Chalvatzaki, Georgia, Churamani, Nikhil, D'Eramo, Carlo, Hamidi, Samin, Hesse, Robin, Hinder, Fabian, Kamath, Roshni Ramanna, Lomonaco, Vincenzo, Paul, Subarnaduti, Pistilli, Francesca, Tuytelaars, Tinne, van de Ven, Gido M, Kersting, Kristian, Schaub-Meyer, Simone, Mundt, Martin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.11927
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910832730832896
author Mitchell, Rupert
Alliegro, Antonio
Camoriano, Raffaello
Carrión-Ojeda, Dustin
Carta, Antonio
Chalvatzaki, Georgia
Churamani, Nikhil
D'Eramo, Carlo
Hamidi, Samin
Hesse, Robin
Hinder, Fabian
Kamath, Roshni Ramanna
Lomonaco, Vincenzo
Paul, Subarnaduti
Pistilli, Francesca
Tuytelaars, Tinne
van de Ven, Gido M
Kersting, Kristian
Schaub-Meyer, Simone
Mundt, Martin
author_facet Mitchell, Rupert
Alliegro, Antonio
Camoriano, Raffaello
Carrión-Ojeda, Dustin
Carta, Antonio
Chalvatzaki, Georgia
Churamani, Nikhil
D'Eramo, Carlo
Hamidi, Samin
Hesse, Robin
Hinder, Fabian
Kamath, Roshni Ramanna
Lomonaco, Vincenzo
Paul, Subarnaduti
Pistilli, Francesca
Tuytelaars, Tinne
van de Ven, Gido M
Kersting, Kristian
Schaub-Meyer, Simone
Mundt, Martin
contents Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental classification tasks, where models learn to classify new categories while retaining knowledge of previously learned ones. Here, we argue that maintaining such a focus limits both theoretical development and practical applicability of CL methods. Through a detailed analysis of concrete examples - including multi-target classification, robotics with constrained output spaces, learning in continuous task domains, and higher-level concept memorization - we demonstrate how current CL approaches often fail when applied beyond standard classification. We identify three fundamental challenges: (C1) the nature of continuity in learning problems, (C2) the choice of appropriate spaces and metrics for measuring similarity, and (C3) the role of learning objectives beyond classification. For each challenge, we provide specific recommendations to help move the field forward, including formalizing temporal dynamics through distribution processes, developing principled approaches for continuous task spaces, and incorporating density estimation and generative objectives. In so doing, this position paper aims to broaden the scope of CL research while strengthening its theoretical foundations, making it more applicable to real-world problems.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continual Learning Should Move Beyond Incremental Classification
Mitchell, Rupert
Alliegro, Antonio
Camoriano, Raffaello
Carrión-Ojeda, Dustin
Carta, Antonio
Chalvatzaki, Georgia
Churamani, Nikhil
D'Eramo, Carlo
Hamidi, Samin
Hesse, Robin
Hinder, Fabian
Kamath, Roshni Ramanna
Lomonaco, Vincenzo
Paul, Subarnaduti
Pistilli, Francesca
Tuytelaars, Tinne
van de Ven, Gido M
Kersting, Kristian
Schaub-Meyer, Simone
Mundt, Martin
Machine Learning
Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental classification tasks, where models learn to classify new categories while retaining knowledge of previously learned ones. Here, we argue that maintaining such a focus limits both theoretical development and practical applicability of CL methods. Through a detailed analysis of concrete examples - including multi-target classification, robotics with constrained output spaces, learning in continuous task domains, and higher-level concept memorization - we demonstrate how current CL approaches often fail when applied beyond standard classification. We identify three fundamental challenges: (C1) the nature of continuity in learning problems, (C2) the choice of appropriate spaces and metrics for measuring similarity, and (C3) the role of learning objectives beyond classification. For each challenge, we provide specific recommendations to help move the field forward, including formalizing temporal dynamics through distribution processes, developing principled approaches for continuous task spaces, and incorporating density estimation and generative objectives. In so doing, this position paper aims to broaden the scope of CL research while strengthening its theoretical foundations, making it more applicable to real-world problems.
title Continual Learning Should Move Beyond Incremental Classification
topic Machine Learning
url https://arxiv.org/abs/2502.11927