The Bottleneck

2021

Subfields: Information Theory

Citations in the corpus

• Semi-supervised sequence tagging with bidirectional language models (2017, neutral): “Other semisupervised learning methods for structured prediction problems include co-training (Blum and Mitchell, 1998; Pierce and Cardie, 2001), expectation maximization (Nigam et al.”
• Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (2019, background): “earning. First, under multi-view learning, the objective is to use multiple views of both the labeled and unlabeled data to train the model. These multiple views can be obtained either from raw text (Blum and Mitchell 1998) or from the features (JZ15b). Second, under data augmentation, as the name i”
• Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (2019, background): “Later works proposed co-training or tri-training that uses two or three models as judges and only keeps examples that all models agree on (Blum and Mitchell, 1998; Zhou and Li, 2005).”
• Self-Training With Noisy Student Improves ImageNet Classification (2019, background): “Apart from self-training, another important line of work in semi-supervised learning [9, 85] is based on consistency training [6, 4, 53, 36, 70, 45, 41, 51, 10, 12, 49, 2, 38, 72, 74, 5, 81].”
• Data-Efficient Image Recognition with Contrastive Predictive Coding (2019, background): “ually sampled randomly. Other approaches to semi-supervised learning train simultaneously on labeled and unlabeled data. Many such works have roots in early work on bootstrapping [57] and co-training [6] from text (see [71] for a survey). An increasingly popular approach in deep learning consists in”
• Contrastive Multiview Coding (2019, background): “Closely related to self-supervised learning is the idea of multi-view learning, which is a general term involving many different approaches such as co-training [6], multi-kernel learning [11] and metric learning [4]; for comprehensive surveys please see [59, 34].”
• Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction (2016, neutral): “The idea of learning representations from multisensory signals also shows up in structure learning [2], cotraining [3], and multi-view learning [46].”
• Revisiting Self-Training for Neural Sequence Generation (2019, background): “For instance, co-training (Blum & Mitchell, 1998) learns models on two independent feature sets of the same data, and assigns confident labels to unlabeled data from one of the models.”
• AutoML: A Survey of the State-of-the-Art (2019, methodology): “[67] summarize the self-labeling methods into the following categories: selftraining [68, 69], co-training [70, 71], and co-learning [72].”
• Toward Causal Representation Learning (2021, background): “Note, moreover, that some of the theoretical results in the field use assumptions well-known from causal graphs (even if they do not mention causality): the cotraining theorem [33] makes a statement about learnability from unlabelled data and”
• Towards Causal Representation Learning (2021, background): “Note, moreover, that some of the theoretical results in the field use assumptions well-known from causal graphs (even if they do not mention causality): the co-training theorem [31] makes a statement about learnability from unlabelled data, and relies on an assumption of predictors being conditional”
• Causality for Machine Learning (2019, background): “Note, moreover, that some of the theoretical results in the field use assumptions well-known from causal graphs (even if they do not mention causality): the co-training theorem (Blum and Mitchell, 1998) makes a statement about learnability from unlabelled data, and relies on an assumption of predict”
• Semi-supervised learning, causality, and the conditional cluster assumption (2019, methodology): “This is a wrapper algorithm that initializes the learner based on the labeled data, updates the labels for the unlabelled data, and then retrains based on all labeled data available, possibly iterating this procedure [9, 10, 11].”
• Adversarial Continual Learning (2020, background): “In the machine learning literature, multi-view learning, aims at constructing and/or using different views or modalities for better learning performances [3,39].”
• Never-Ending Learning (2015, positive): “Theoretical characterizations of cotraining (Blum and Mitchell 1998) and other multitask learning methods (Balcan and Blum 2004; Platanios, Blum, and Mitchell 2014) have provided insights into when and how the sample complexity of learning problems can be improved via multitask learning.”
• A Theoretical Analysis of Contrastive Unsupervised Representation Learning (2019, methodology): “Though reminiscent of past ideas – e.g. kernel learning, metric learning, co-training (Cortes et al., 2010; Bellet et al., 2013; Blum & Mitchell, 1998) – these algorithms lack a theoretical framework quantifying when and why they work.”
• Alignment by Agreement (2006, neutral): “Our approach is similar in spirit to co-training, where two classifiers, complementary by the virtue of having different views of the data, are trained jointly to encourage agreement (Blum and Mitchell, 1998; Collins and Singer, 1999).”
• A Comprehensive Survey on Transfer Learning (2019, methodology): “By the way, there are some other methods of providing pseudo labels such as co-training [71], [72] and tri-training [73], [74].”