2020/07/02 by Zhongzheng Ren, Raymond A. Yeh, Ren, Zhongzheng +3 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Multimodal Machine Learning Applications #Natural Language Processing Techniques
paper · pdf · doi:10.48550/arxiv.2007.01293
openalex publication_date 2020/07/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.