An Improved Multi-task Learning Approach with Applications in Medical Diagnosis

By Jinbo Bi, Tao Xiong, Shipeng Yu, Murat Dundar, R. B. Rao. 2008

121 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

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

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico study (2010, background): “Recently, researchers have begun to resort to the multi-task learning model to solve biological problems, such as medical diagnosis, tumor classification and drug screening [48-50].”
Active Lifelong Learning With "Watchdog" (2018, background): “In this setting, dramatic successes have been achieved in many areas by utilizing MTL, such as medical diagnosis (Bi et al. 2008), handwritten character recognition (Obozinski, Taskar, and Jordan 2007), relative attributes learning (Chen, Zhang, and Li 2014) and text classification ∗This work is…”
Probabilistic Multi-Task Feature Selection (2010, methodology): “The objective functions of most existing multi-task feature selection methods [24, 17, 28, 1, 2, 15, 20, 16, 18] can be expressed in the following form:”
Machine Learning and Radiology (2012, background): “A typical example of a multi-task CAD system can be found in the work of Bi et al. (2008).”
Multi-Modal Multi-Task Learning for Joint Prediction of Multiple Regression and Classification Variables in Alzheimer’s Disease (2011, methodology): “…the existing multi-task learning methods: (1) sharing parameters or prior distributions of the hyperparameters of the models across multiple tasks (Bi et al., 2008), and 2) sharing a common underlying representation across multiple tasks (Argyriou et al., 2008; Obozinski et al., 2006; Yang et…”
Transfer Learning for Molecular Cancer Classification Using Deep Neural Networks (2019, background): “An example of its use can be seen in [21] where shared feature representations are learned to detect abnormal structures in medical images.”
On Multiplicative Multitask Feature Learning (2014, methodology): “The ﬁrst two settings ( p, k ) = (2 , 2) , (1 , 1) give the same methods respectively in [2, 14], and the last two settings correspond to our new formulations.”
Feature Selection (2016, background): “This problem can be solved by the l2,1-norm regularization which is widely applied in many applications (Obozinski et al., 2007; Evgeniou and Pontil, 2007; Bi et al., 2008; Zhang et al., 2008).”
$\ell_{p}-\ell_{q}$ Penalty for Sparse Linear and Sparse Multiple Kernel Multitask Learning (2011, background): “Application domains that have been shown to benefit from MTL are medical diagnosis [ 5 ], drug therapy prediction [6], vaccine design [22], and conjoint analysis [1].”
Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, methodology): “[2017] mass detection, classification different same feature, pretraining Lung Bi et al. [2008] abnormality classification different same feature, multi-task Schlegl et al. [2014] lung tissue classification different same/different feature, pretraining Shen et al. [2016] lung cancer malignancy predi”
Multi-Task Feature Learning Via Efficient l2, 1-Norm Minimization (2009, methodology): “Multi-task learning [1, 2, 3, 7, 17, 18, 19, 26, 28] has recently received increasing attention in machine learning, artificial intelligence, and computer vision.”