Semi-Supervised Learning

By Chapelle, Olivier Chapelle, B Scholkopf, Bernhard Schölkopf, Zien, Alexander Zien. 2009

616 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Media Technology, Representation & Self-Supervised Learning

How researchers see this paper

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

In Control and Systems Engineering

In Media Technology

In Representation & Self-Supervised Learning

Citations in the corpus

Unsupervised Data Augmentation for Consistency Training (2019, background): “Semi-supervised learning (SSL) [1] is one of the most promising paradigms of leveraging unlabeled data to address this weakness.”
Self-Training With Noisy Student Improves ImageNet Classification (2019, background): “Apart from self-training, another important line of work in semi-supervised learning [12, 103] is based on consistency training [5, 64, 47, 84, 56, 52, 62, 13, 16, 60, 2, 49, 88, 91, 8, 98, 46, 7].”
Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, background): “a is often readily accessible and available in large quantities. The idea of semi-supervised learning is to leverage unlabeled data to improve task performance when few labeled examples are available [10,70]. One class of semisupervised techniques consists in propagating the knowledge learned from t”
Novel Class Discovery without Forgetting (2022, background): “In semi-supervised learning approaches [10,52], the labeled and unlabeled data comes from the same set of classes.”
Attention-based Graph Neural Network for Semi-supervised Learning (2018, background): “A more thorough survey on using non-neural network methods for semi-supervised learning can be found in [12].”
Smooth Neighbors on Teacher Graphs for Semi-Supervised Learning (2017, background): “nts over state-of-the-art results while the extra time cost is negligible. 2. Related work Using unlabeled data to improve generalization has a long and rich history and the literature in SSL is vast [52, 9]. So in this section we focus on reviewing the closely related papers, especially the recent ”
Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation (2020, methodology): “We adopt the idea of self-training from semi-supervised learning [13] for model adaptation.”
Ensemble deep learning: A review (2021, background): “Semi-supervised learning [145, 146] is a machine learning method that falls between supervised and unsupervised learning.”
Unsupervised Data Augmentation (2019, methodology): “On this direction, semi-supervised learning [Chapelle et al., 2009] is one of the most promising methods and recent works can be grouped into three categories: (1) graph-based label propagation via graph convolution [Kipf and Welling, 2016] and graph embeddings [Weston et al.”
Bootstrapping Conversational Agents With Weak Supervision (2018, background): “Given that, signiﬁcant research effort has been made on reducing labeling effort, including work on semi-supervised learning (Chapelle, Scholkopf, and Zien 2009), active learning (Settles 2012), and transfer learning (Pan, Yang, and others 2010).”
Machine Learning on Graphs: A Model and Comprehensive Taxonomy (2020, methodology): “We review two types of semi-supervised [23] graph regularization approaches: methods that use random walks to regularize embeddings and Laplacian-based regularization methods.”
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss (2019, background): “This is referred to as the cluster assumption in the semi-supervised learning literature (Chapelle et al., 2009).”
Learning User-Preferred Mappings for Intuitive Robot Control (2020, methodology): “Accordingly—to tackle the challenge of insufficient labeled data—we employ a semi-supervised learning method [22].”
Towards Deeper Graph Neural Networks (2020, background): “rary for deep learning on irregularly structured data built upon Pytorch. We consider the following baselines: Logistic Regression (LogReg), Multilayer Perceptron (MLP), Label Propagation (LabelProp) [2], Normalized Laplacian Label Propagation (LabelProp NL) [2], ChebNet[4],GraphConvolutionalNetwork”