Recursive regularization for large-scale classification with hierarchical and graphical dependencies

By Siddharth Gopal, Yiming Yang. 2013

158 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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. Himanshu Jain
2. Yashoteja Prabhu
3. Yangqiu Song
4. Manik Varma
5. Qiang Yang
6. Hao Peng
7. Lihong Wang
8. Yaopeng Liu

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Yangqiu Song
3. Himanshu Jain
4. Manik Varma
5. Hao Peng
6. Lihong Wang
7. Yaopeng Liu
8. Jianxin Li

Citations in the corpus

• Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN (2018, methodology): “This again verifies why the authors of [13] used an extended problem of RCV1 rather than the original 103 classes to apply recursive regularization.”
• Extreme Multi-label Loss Functions for Recommendation, Tagging, Ranking & Other Missing Label Applications (2016, background): “As such, the Hamming loss [4, 6, 9, 10, 13, 18, 21, 39, 42, 47] continues to be one of the most popular losses for extreme multi-label learning along with precision [3, 5, 17, 20, 21, 33, 44, 45] and the F-measure [4, 10, 14, 18, 19, 21, 39, 49].”