Online Multitask Relative Similarity Learning

By Shuji Hao, Peilin Zhao, Yong Liu, Steven C. H. Hoi, Chunyan Miao. 2017

14 citations recorded by the source corpus.

Relative similarity learning (RSL) aims to learn similarity functions from data with relative constraints. Most previous algorithms developed for RSL are batch-based learning approaches which suffer from poor scalability when dealing with real-world data arriving sequentially. These methods are often designed to learn a single similarity function for a specific task. Therefore, they may be sub-optimal to solve multiple task learning problems. To overcome these limitations, we propose a scalable RSL framework named OMTRSL (Online Multi-Task Relative Similarity Learning). Specifi-cally, we first develop a simple yet effective online learning algorithm for multi-task relative similarity learning. Then, we also propose an active learning algorithm to save the labeling cost. The proposed algorithms not only enjoy theoretical guarantee, but also show high efficacy and efficiency in extensive experiments on real-world datasets.

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. Qiang Yang
2. Jindong Wang
3. Yu Zhang
4. Yiqiang Chen
5. Peilin Zhao
6. Wenjie Feng
7. Steven C. H. Hoi
8. Shuji Hao

In Computer Vision and Pattern Recognition

1. Jindong Wang
2. Qiang Yang
3. Yiqiang Chen
4. Yu Zhang
5. Doyen Sahoo
6. Peilin Zhao
7. Steven C. H. Hoi
8. Wenjie Feng

Citations in the corpus

• A Survey on Multi-Task Learning (2017, methodology): “In [184], a multi-task passive-aggressive method is proposed to learn multiple relative similarity”
• Online Learning: A Comprehensive Survey (2018, methodology): “…the query strategy is a margin-based sampling approach without explicitly exploiting the second-order information: Pr(Zt+1 = 1) = I(pt ≤ 4 ln t∑t−1 i=1 Zi ) Hao et al. (2016, 2017a) proposed second-order online active learning algorithms by fully exploiting both the first-order and second-order…”
• Balanced Distribution Adaptation for Transfer Learning (2017, background): “Transfer learning has been widely applied to activity recognition [8], incremental learning [9], and online learning [10], [11].”