GML begins with some easy instances in a task, which can be automatically labeled by the machine with high accuracy, and then gradually reasons about the labels of the more challenging instances based on the observations provided by the labeled instances. The following two properties of GML make it fundamentally different from the existing learning paradigms:
The scenario of gradual machine learning does not satisfy the i.i.d (independent and identically distributed) assumption underlying most existing machine learning models: the labeled easy instances are not representative of the unlabeled hard instances. The distribution misalignment between the labeled and unlabeled instances renders most existing learning models unfit for gradual machine learning.
Gradual machine learning proceeds in small stages. At each stage, it typically labels only one instance based on the evidential certainty provided by the labeled easier instances. The process of iterative labeling can be performed in an unsupervised manner without requiring any human intervention.
Gradual machine learning is a new and promising research direction supposed to complement deep learning. We have successfully applied gradual machine learning to the classification tasks of entity resolution and sentiment analysis. As a general paradigm, GML can be generalized to various classification tasks. We have also initiated an open-source project, at https://github.com/gml-explore/numbskull, to support GML application and implementation.
@inproceedings{hou2019gradual,
title={Gradual machine learning for entity resolution},
author={Hou, Boyi and Chen, Qun and Shen, Jiquan and Liu, Xin and Zhong, Ping and Wang, Yanyan and Chen, Zhaoqiang and Li, Zhanhuai},
booktitle={The World Wide Web Conference},
pages={3526--3530},
year={2019},
organization={ACM}
}
@article{wang2019joint,
title={Joint Inference for Aspect-level Sentiment Analysis by Deep Neural Networks and Linguistic Hints},
author={Wang, Yanyan and Chen, Qun and Ahmed, Murtadha and Li, Zhanhua and Pan, Wei and Liu, Hailong},
journal={IEEE Transactions on Knowledge and Data Engineering},
year={2019},
publisher={IEEE}
}