Task-Agnostic Experts Composition for Continual Learning
This work addresses the need for more efficient and sustainable AI frameworks, though it appears incremental as it builds on existing compositional methods.
The paper tackled the problem of improving neural networks' compositionality for efficient AI by proposing a zero-shot ensemble of expert models, achieving higher accuracy with less computational resources than baseline algorithms.
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.