Semi-Supervised Multitask Learning

By Qiuhua Liu, Xuejun Liao, Lawrence Carin. 2007

95 citations recorded by the source corpus.

How researchers see this paper

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

1. Mingsheng Long
2. Luc Van Gool
3. Jianmin Wang
4. Dacheng Tao
5. Qiang Yang
6. Yu Zhang
7. Yoshua Bengio
8. Yi Yang

Citations in the corpus

• An Overview of Multi-task Learning (2018, neutral): “Formulti-tasksemi-supervisedclassification,amethodpro-posedin[63,64]followsthetask-clusteringap-proachtodotaskclusteringondifferenttasksbased onarelaxedDirichletprocess,whileineachtask, randomwalkisusedtoexploitusefulinformation containedintheunlabeleddata.”
• A Survey on Multi-Task Learning (2017, methodology): “tive learning to utilize unlabeled data for MTL by using the Fisher information as a criterion to select unlabeled data to acquire their labels with the semi-supervised multi-task classification model [117], [118] as the classifier for multiple tasks. MTL achieves the performance improvement in not on”
• Adaptation Regularization: A General Framework for Transfer Learning (2014, background): “4) Parameter Sharing + Manifold Regularization: This strategy is explored by semi-supervised multi-task learning methods [32], [33], which aim to improve the performance of multiple related tasks by exploring the common structure through a common prior.”
• Semi-Supervised Multi-Task Regression (2009, methodology): “[20] proposed a semi-supervised learning method called parameterized neighborhood-based classification (PNBC), which applies random walk to logistic regression and uses a task clustering method for multi-task learning.”
• Introduction to Semi-Supervised Learning (2009, background): “• inferring label sampling mechanisms [146], multi-instance learning [207], multi-task learning [116], and deep learning [141, 185];”
• Semi-supervised multi-task learning of structured prediction models for web information extraction (2011, background): “There has been a significant amount of work on multi-task learning [6, 14, 13, 4, 22, 16].”
• A Graphbased Framework for Multi-Task Multi-View Learning (2011, methodology): “…assume that the function parameters for different tasks are similar, such as the kernel methods for learning multiple tasks (Evgeniou et al., 2005), the semi-supervised multi-task learning framework (Liu et al., 2007), the clustered multi-task learning algorithm (Jacob et al., 2008), etc.”
• Coupled semi-supervised learning for information extraction (2010, methodology): “Semi-supervised multitask learning has used a prior that encourages related models to have similar parameters [15].”
• Multi-Task Learning for Dense Prediction Tasks: A Survey (2020, background): “This includes various domains, such as language [24], [98], [99], audio [100], video [101], [102], and robotics [103], [104], as well as with different learning paradigms, such as reinforcement learning [105], [106], self-supervised learning [107], semisupervised learning [108], [109] and active lea”