Learning for Tail Label Data: A Label-Specific Feature Approach

By Tong Wei, Wei-Wei Tu, Yu-Feng Li. 2019

21 citations recorded by the source corpus.

Tail label data (TLD) is prevalent in real-world tasks, and large-scale multi-label learning (LMLL) is its major learning scheme. Previous LMLL studies typically need to additionally take into account extensive head label data (HLD), and thus fail to guide the learning behavior of TLD. In many applications such as recommender systems, however, the prediction of tail label is very necessary, since it provides very important supplementary information. We call this kind of problem as \emph{tail label learning}. In this paper, we propose a novel method for the tail label learning problem. Based on the observation that the raw feature representation in LMLL data usually benefits HLD, which may not be suitable for TLD, we construct effective and rich label-specific features through exploring labeled data distribution and leveraging label correlations. Specifically, we employ clustering analysis to explore discriminative features for each tail label replacing the original high-dimensional and sparse features. In addition, due to the scarcity of positive examples of TLD, we encode knowledge from HLD by exploiting label correlations to enhance the label-specific features. Experimental results verify the superiority of the proposed method in terms of performance on TLD.

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. Dacheng Tao
2. Liu Liu
3. Zhen Wang
4. Yiqun Duan
5. Tong Wei
6. Yu-Feng Li
7. Jing Zhang
8. Charu C. Aggarwal

In Computer Vision and Pattern Recognition

1. Liu Liu
2. Dacheng Tao
3. Zhen Wang
4. Yiqun Duan
5. Yu-Feng Li
6. Luc Van Gool
7. Ming-Hsuan Yang
8. Changxing Ding

Citations in the corpus

• Continual Learning through Retrieval and Imagination (2022, methodology): “Although co-sine normalization has been adopted in other visual problem (Gidaris et al. 2018; Wei et al. 2019; Guo et al. 2020; Qi et al. 2018; Hou et al. 2019), we demonstrate that it can effectively eliminate the imbalance in the magnitude of class embeddings and facilitate continual learning…”
• Probabilistic Label Tree for Streaming Multi-Label Learning (2021, background): “Most extant multi-label learning studies focus on a fixed set of labels [1, 13, 20, 26–29, 34, 36, 37].”