Development and Comparison of Scoring Functions in Curriculum Learning

TL;DR

This paper compares various scoring functions for curriculum learning across image and text datasets, highlighting the effectiveness of transfer learning-based functions for images and suggesting potential for new functions in text tasks.

Contribution

It introduces a comparative analysis of scoring functions in curriculum learning, emphasizing transfer learning's benefits for image datasets and identifying the need for new functions in text classification.

Findings

Transfer learning-based scoring functions outperform classical methods on image datasets.

No significant difference between scoring functions on text datasets.

Potential for developing new scoring functions for text classification tasks.

Abstract

Curriculum Learning is the presentation of samples to the machine learning model in a meaningful order instead of a random order. The main challenge of Curriculum Learning is determining how to rank these samples. The ranking of the samples is expressed by the scoring function. In this study, scoring functions were compared using data set features, using the model to be trained, and using another model and their ensemble versions. Experiments were performed for 4 images and 4 text datasets. No significant differences were found between scoring functions for text datasets, but significant improvements were obtained in scoring functions created using transfer learning compared to classical model training and other scoring functions for image datasets. It shows that different new scoring functions are waiting to be found for text classification tasks.