CurML: A Curriculum Machine Learning Library
Authors:
Open Access
- 10 October 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 7359-7363
Abstract
Curriculum learning (CL) is a machine learning paradigm gradually learning from easy to hard, which is inspired by human curricula. As an easy-to-use and general training strategy, CL has been widely applied to various multimedia tasks covering images, texts, audios, videos, etc. The effectiveness of CL has recently facilitated an increasing number of new CL algorithms. However, there has been no open-source library for curriculum learning, making it hard to reproduce, evaluate and compare the numerous CL algorithms on fair benchmarks and settings. To ease and promote future research on CL, we develop CurML, the first Curriculum Machine L earning library to integrate existing CL algorithms into a unified framework. It is convenient to use and flexible to customize by calling the provided five APIs, which are designed for easily plugging into a general training process and conducting the data-oriented, model-oriented and loss-oriented curricula. Furthermore, we present empirical results obtained by CurML to demonstrate the advantages of our library. The code is available online at https://github.com/THUMNLab/CurML.Keywords
Funding Information
- National Key Research and Development Program of China (No. 2020AAA0106300)
- National Natural Science Foundation of China (No. 62250008, No. 62102222)
This publication has 10 references indexed in Scilit:
- Adaptive Curriculum Learning for Video CaptioningIEEE Access, 2022
- Causal Inference with Knowledge Distilling and Curriculum Learning for Unbiased VQAACM Transactions on Multimedia Computing, Communications, and Applications, 2022
- Adaptive Curriculum Learning2021
- A Survey on Curriculum LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation2020
- Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks2019
- Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene UnderstandingInternational Journal of Computer Vision, 2019
- Why curriculum learning & self-paced learning work in big/noisy data: A theoretical perspectiveBig Data and Information Analytics, 2015
- Curriculum learning2009
- ImageNet: A large-scale hierarchical image database2009