High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction

By Hua Wang, Feiping Nie, Heng Huang, Jingwen Yan, Sungeun Kim, Shannon L. Risacher, Andrew J. Saykin, Li Shen. 2012

76 citations recorded by the source corpus.

Subfields: Evaluation & Benchmarks

How researchers see this paper

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

In Evaluation & Benchmarks

1. Qiang Yang
2. Feiping Nie
3. Peter F. Schulam
4. Heng Huang
5. Suchi Saria
6. Hua Wang
7. Yu Zhang

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “…measures in Alzheimer’s disease [109], identification of longitudinal phenotypic markers for Alzheimer’s disease progression prediction [110], prioritization of disease genes [111], biological image analysis based on natural images [20], survival analysis [112], and multiple genetic…”
• A Survey on Multi-Task Learning (2017, background): “In [191], the identification of longitudinal phenotypic markers for the Alzheimers disease progression prediction is formulated as a multi-task time-series problem where at each time point, a learner is associated with parameters organized in a matrix and the parameter tensor consisting parameter ma”
• A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure (2015, methodology): “This has been applied to modeling trajectories by treating predictions at each time point as a separate task and enforcing similarity between submodels close in time [14].”
• Robust and Discriminative Self-Taught Learning (2013, methodology): “(14) Because it can be verified that (Wang et al., 2012d) for function f (x) = x − x 2 2α , given any x = α ∈ R, f (x) ≤ f (α) holds, together with the definitions of U (t) and V (t) k (1 ≤ k ≤ K), we can derive that ( X − D (t+1) A (t+1) ) T 2,1 − T r(( X − D (t+1) A (t+1) )U (t) ( X − D (t+1) A…”
• Modeling disease progression via multi-task learning (2013, unknown): “When data from multiple time points are available, advanced structured sparsity techniques can be used to leverage the temporal information among features, e.g., (Wang et al., 2012; Zhang and Shen, 2012).”
• Multi-View Clustering and Feature Learning via Structured Sparsity (2013, methodology): “To address this, we use group ℓ1norm (G1-norm) for regularization, which is defined as ∥W∥G1 = c∑ i=1 k∑ j=1 ||wji ||2 (Wang et al., 2012b; 2013) and illustrated in Figure 1.”