Multilabel dimensionality reduction via dependence maximization

By Yin Zhang, Zhi-Hua Zhou. TKDD, 2008

403 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

View Paper: https://www.semanticscholar.org/paper/7793e3f51f3c373bd75f9768e927ff6632fe8d69

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

1. Zhi-Hua Zhou
2. Ioannis P. Vlahavas
3. Grigorios Tsoumakas
4. Ioannis Manousos Katakis
5. James T. Kwok
6. Yue Zhu
7. Xin Shu
8. Liang Tao

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Bernard Ghanem
4. Ming-Hsuan Yang
5. Trevor Darrell
6. Xiaogang Wang
7. Andrea Vedaldi
8. Andrew Zisserman

In Information Systems

1. James T. Kwok
2. Zhi-Hua Zhou
3. Yue Zhu
4. Baoyuan Wu
5. Grigorios Tsoumakas
6. Ioannis P. Vlahavas
7. Xiangnan Kong
8. Michael Kwok-Po Ng

Citations in the corpus

• Multi-Label Learning with Global and Local Label Correlation (2017, background): “Others estimate label correlations by label co-occurrence in the training data [13], or equivalently constructing a label kernel [48].”
• Mining Multi-label Data (2010, methodology): “A version of the LSI method that takes into consideration label information (MLSI) was proposed in [49], while a supervised multi-label feature extraction algorithm based on the Hilbert-Schmidt independence criterion was proposed in [50].”
• Learning shared subspace for multi-label dimensionality reduction via dependence maximization (2015, methodology): “Wang et al. [26] proposed a novel multilabel linear discriminant analysis (MLDA) to take advantage of label correlation and explore the powerful discrimination ability to cope with multi-label DR. Zhang and Zhou [27] developed a multi-label dimensionality reduction via dependence maximization.”
• Sufficient Component Analysis for Supervised Dimension Reduction (2011, methodology): “Below, we compare SCA, Multi-label Dimensionality reduction via Dependence Maximization (MDDM) 4 (Zhang & Zhou, 2010), Canonical Correlation Anal-4 ysis (CCA) 5 (Hotelling, 1936), and Principal Component Analysis (PCA) 6 (Bishop, 2006).”
• A Deep Matrix Factorization Method for Learning Attribute Representations (2015, methodology): “…(4) present the Deep WSF model that can use already known (partial) information for the attributes of our data distribution to extract better features for our model, and (5) demonstrate how to improve the performance of Deep Semi-NMF , by using the existing weights from a trained Deep WSF model.”
• Transductive Multilabel Learning via Label Set Propagation (2013, methodology): “reduction approach (MDDM [36]) is used before using kd-tree”
• Multi-label Learning with Missing Labels Using Mixed Dependency Graphs (2018, methodology): “ compared, but here we choose to remove the comparisons with them, due to their much higher costs on both computation and memory than other compared methods. Evaluationmetrics. Average precision (AP) [60] is adopted to measure the ranking performance of the predicted labels of each instance, i.e., t”