Task-Agnostic Experts Composition for Continual Learning
By: Luigi Quarantiello, Andrea Cossu, Vincenzo Lomonaco
Potential Business Impact:
AI learns to solve hard problems by breaking them down.
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.
Similar Papers
Separating the what and how of compositional computation to enable reuse and continual learning
Machine Learning (CS)
Teaches computers to learn new skills without forgetting old ones.
Scalable Evaluation and Neural Models for Compositional Generalization
Machine Learning (CS)
Teaches computers to understand new things from old.
Compose by Focus: Scene Graph-based Atomic Skills
Robotics
Robots learn to combine simple actions for new tasks.