Score: 0

Task-Agnostic Experts Composition for Continual Learning

Published: June 18, 2025 | arXiv ID: 2506.15566v1

By: Luigi Quarantiello, Andrea Cossu, Vincenzo Lomonaco

Potential Business Impact:

AI learns to solve hard problems by breaking them down.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇮🇹 Italy

Page Count
5 pages

Category
Computer Science:
Machine Learning (CS)