Aggregated f-average Neural Network applied to Few-Shot Class Incremental Learning

TL;DR

This paper introduces an aggregated f-average neural network that combines ensemble learning techniques to improve few-shot class incremental learning, emphasizing interpretability and simplicity.

Contribution

It proposes a novel AFA neural network that models and combines various averages for optimal ensemble prediction in incremental learning.

Findings

Good performance on few-shot class incremental learning tasks

Interpretable architecture and simple training strategy

Effective fusion of ensemble averaging methods

Abstract

Ensemble learning leverages multiple models (i.e., weak learners) on a common machine learning task to enhance prediction performance. Basic ensembling approaches average the weak learners outputs, while more sophisticated ones stack a machine learning model in between the weak learners outputs and the final prediction. This work fuses both aforementioned frameworks. We introduce an aggregated f-average (AFA) shallow neural network which models and combines different types of averages to perform an optimal aggregation of the weak learners predictions. We emphasise its interpretable architecture and simple training strategy, and illustrate its good performance on the problem of few-shot class incremental learning.