Degrees of supervision

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Loss factorization, weakly supervised learning and label noise robustness (2016, background): “In this scenario, training labels are only partially observable due to an unknown noise process [Garcıa-Garcıa and Williamson, 2011, Hernandez-Gonzalez et al., 2016].”
A brief introduction to weakly supervised learning (2018, background): “partially supervised learning focuses mostly on learning with incomplete supervision [95], and there have been some other discussions about weak supervision [96,97].”