Dynamic Data Selection for Curriculum Learning via Ability Estimation

by   John P. Lalor, et al.

Curriculum learning methods typically rely on heuristics to estimate the difficulty of training examples or the ability of the model. In this work, we propose replacing difficulty heuristics with learned difficulty parameters. We also propose Dynamic Data selection for Curriculum Learning via Ability Estimation (DDaCLAE), a strategy that probes model ability at each training epoch to select the best training examples at that point. We show that models using learned difficulty and/or ability outperform heuristic-based curriculum learning models on the GLUE classification tasks.


page 1

page 2

page 3

page 4


Statistical Measures For Defining Curriculum Scoring Function

Curriculum learning is a training strategy that sorts the training examp...

Improving Imbalanced Text Classification with Dynamic Curriculum Learning

Recent advances in pre-trained language models have improved the perform...

Curriculum Learning with Diversity for Supervised Computer Vision Tasks

Curriculum learning techniques are a viable solution for improving the a...

Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration

Curriculum learning needs example difficulty to proceed from easy to har...

Curriculum Learning for Graph Neural Networks: A Multiview Competence-based Approach

A curriculum is a planned sequence of learning materials and an effectiv...

Dynamic curriculum learning via data parameters for noise robust keyword spotting

We propose dynamic curriculum learning via data parameters for noise rob...

An Empirical Comparison of Syllabuses for Curriculum Learning

Syllabuses for curriculum learning have been developed on an ad-hoc, per...

Please sign up or login with your details

Forgot password? Click here to reset