# Learning to Impute: A General Framework for Semi-supervised Learning Source: [Learning to Impute: A General Framework for Semi-supervised Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:37:00.137Z Authors: Wei-Hong Li, Chuan-Sheng Foo, Hakan Bilen Published: 2019-12-22T00:27:21.000Z ## Abstract Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this paper, we take a more direct approach for semi-supervised learning and propose learning to impute the labels of unlabeled samples such that a network achieves better generalization when it is trained on these labels. We pose the problem in a learning-to-learn formulation which can easily be incorporated to the state-of-the-art semi-supervised techniques and boost their performance especially when the labels are limited. We demonstrate that our method is applicable to both classification and regression problems including image classification and facial landmark detection tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()