# Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning Source: [Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:40:59.400Z Authors: Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing Published: 2020-07-02T17:59:05.000Z ## Abstract Existing semi-supervised learning (SSL) algorithms use a single weight to balance the loss of labeled and unlabeled examples, i.e., all unlabeled examples are equally weighted. But not all unlabeled data are equal. In this paper we study how to use a different weight for every unlabeled example. Manual tuning of all those weights -- as done in prior work -- is no longer possible. Instead, we adjust those weights via an algorithm based on the influence function, a measure of a model's dependency on one training example. To make the approach efficient, we propose a fast and effective approximation of the influence function. We demonstrate that this technique outperforms state-of-the-art methods on semi-supervised image and language classification 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. - [Image Classification on SVHN (test) (Top-1 Error Rate)](): Image Classification; SVHN (test); Top-1 Error Rate: 2.32. - [Image Classification on CIFAR-10 standard (test) (Top-1 Error Rate)](): Image Classification; CIFAR-10 standard (test); Top-1 Error Rate: 4.35. ## Original sources and implementation [Original paper]() [PDF]()