Task-Agnostic Experts Composition for Continual Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quarantiello, Luigi, Cossu, Andrea, Lomonaco, Vincenzo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915350187081728
author Quarantiello, Luigi
Cossu, Andrea
Lomonaco, Vincenzo
author_facet Quarantiello, Luigi
Cossu, Andrea
Lomonaco, Vincenzo
contents Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also for neural networks, especially when aiming for a more efficient and sustainable AI framework. We propose a compositional approach by ensembling zero-shot a set of expert models, assessing our methodology using a challenging benchmark, designed to test compositionality capabilities. We show that our Expert Composition method is able to achieve a much higher accuracy than baseline algorithms while requiring less computational resources, hence being more efficient.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15566
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Task-Agnostic Experts Composition for Continual Learning
Quarantiello, Luigi
Cossu, Andrea
Lomonaco, Vincenzo
Machine Learning
Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also for neural networks, especially when aiming for a more efficient and sustainable AI framework. We propose a compositional approach by ensembling zero-shot a set of expert models, assessing our methodology using a challenging benchmark, designed to test compositionality capabilities. We show that our Expert Composition method is able to achieve a much higher accuracy than baseline algorithms while requiring less computational resources, hence being more efficient.
title Task-Agnostic Experts Composition for Continual Learning
topic Machine Learning
url https://arxiv.org/abs/2506.15566