SELF-LLP: Self-supervised learning from label proportions with self-ensemble

作者:

Highlights:

• A self-supervised learning is introduced to LLP, which leverages the advantage of self-supervision in representation learning to facilitate learning with weakly-supervised labels.

• A self-ensemble strategy is employed to provide pseudo “supervised” information to guide the training process by aggregating the predictions of multiple previous network evaluations.

• Although the employed self-supervised mechanism is image-specific, we seamlessly fit our framework to tabular datasets by incorporating orthogonal matrix transformation into the rotation-based self-supervised strategy.

• Thanks to the self-supervised and self-ensemble mechanisms, our algorithm takes much less epochs to reach convergence and obtain better performance, compared with previous LLP solvers.

摘要

•A self-supervised learning is introduced to LLP, which leverages the advantage of self-supervision in representation learning to facilitate learning with weakly-supervised labels.•A self-ensemble strategy is employed to provide pseudo “supervised” information to guide the training process by aggregating the predictions of multiple previous network evaluations.•Although the employed self-supervised mechanism is image-specific, we seamlessly fit our framework to tabular datasets by incorporating orthogonal matrix transformation into the rotation-based self-supervised strategy.•Thanks to the self-supervised and self-ensemble mechanisms, our algorithm takes much less epochs to reach convergence and obtain better performance, compared with previous LLP solvers.

论文关键词:Learning from label proportion,Self-supervised learning,Self-ensemble strategy,Multi-task learning

论文评审过程:Received 13 March 2021, Revised 22 April 2022, Accepted 30 April 2022, Available online 2 May 2022, Version of Record 15 May 2022.

论文官网地址:https://doi.org/10.1016/j.patcog.2022.108767