Deep Extreme Multi-label Learning

By Wenjie Zhang, Liwei Wang, Junchi Yan, Xiangfeng Wang, Hongyuan Zha. 2017

133 citations recorded by the source corpus.

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data. The main challenge lies in the exponential label space which involves 2L possible label sets especially when the label dimension L is huge, e.g., in millions for Wikipedia labels. This paper is motivated to better explore the label space by originally establishing an explicit label graph. In the meanwhile, deep learning has been widely studied and used in various classification problems including multi-label classification, however it has not been properly introduced to XML, where the label space can be as large as in millions. In this paper, we propose a practical deep embedding method for extreme multi-label classification, which harvests the ideas of non-linear embedding and graph priors-based label space modeling simultaneously. Extensive experiments on public datasets for XML show that our method performs competitive against state-of-the-art result.

Subfields: Artificial Intelligence, Molecular Biology

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. Hongyuan Zha
2. Yangqiu Song
3. Tal Ridnik
4. Asaf Noy
5. Xiaofeng He
6. Wei Zhang
7. Qiang Yang
8. Lihi Zelnik-Manor

In Molecular Biology

1. Hongyuan Zha
2. Qiang Yang
3. Xiaofeng He
4. Yangqiu Song
5. Hao Peng
6. Wei Zhang
7. Chris H. Q. Ding
8. Tao Li

Citations in the corpus

• Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN (2018, background): “[47] adopted a general setting for large-scale label set classification but the text data they used have been preprocessed, which means the characteristics of texts is not considered.”
• Asymmetric Loss For Multi-Label Classification (2020, background): “eratedlabels. The scale of Open Images is much larger than previous multi-label datasets such as NUS-WIDE, Pascal-VOC and MS-COCO, allowing us to test ASL on extreme classification multilabel scenario [37]. Full dataset and training details appear in the appendix. To the best of our knowledge, no res”
• Personalized Prescription for Comorbidity (2018, methodology): “We use the common metrics of multi-label, which contains micro under the ROC curve (micro-AUC), macro under the ROC curve (macro-AUC), label ranking average precision score and label ranking loss to promise fair and honest evaluation [31,32].”