/   Home   /   Newsroom   /   Research News

Researchers Propose Lifelong Metric Learning for Smarter Online Learning

Jul 11, 2019     Email"> PrintText Size

Online metric/similarity learning has been widely used in data mining, information retrieval, and computer vision, mainly due to its high efficiency and scalability to large-scale dataset. Unlike most existing batch learning methods that learn metric model offline with all training samples, online learning aims to exploit of one or a group of samples to update the metric model iteratively, and is ideal for tasks in which data arrives sequentially.

However, most state-of-the art online metric learning models can only achieve online learning from fixed predefined t (t > 0) metric learning tasks and cannot add the new task.

In a study published in IEEE Transactions on Cybernetics, CONG Yang's team at Shenyang Institute of Automation of the Chinese Academy of Sciences proposed a lifelong metric learning (LML) to mimic “human learning”, i.e., endowing a new capability to the learned metric for a new task from new online samples and incorporating previous experiences and knowledge.

The LML maintains a common subspace for all learned metrics, namely lifelong dictionary. It is capable of transferring knowledge from the common subspace, in order to learn each new metric learning task with task-specific idiosyncrasy, and can redefine the common subspace over time, maximizing performance across all metric tasks.

Through extensive experiments on several multitask datasets, the research team verified that the proposed framework are well suited to the lifelong learning problem, and exhibited prominent performance in both effectiveness and efficiency.


Demonstration of the LML (Image by CONG yang) 

(Editor: LIU Jia)


Related Articles

polycomb protein;hippocampal;learning;memory

Polycomb Protein EED Plays a Starring Role in Hippocampal Development

Jun 13, 2019

A team led by Prof. LIU Changmei from the Institute of Zoology has shown that the PcG protein EED is essential for the proper formation of the DG. This study establishes EED as an important modulator of hippocampal development and provides novel mechan...

Asian hornet;Vespa velutina;learning;odor detection;olfactory learning;memory

Asian Hornets Possess Olfactory Learning and Long-term Olfactory Memory

Jun 06, 2019

In a recent issue of Journal of Experimental Biology, researchers from Xishuangbanna Tropical Botanical Garden (XTBG) provided the first evidence of olfactory learning and long-term olfactory memory in all three castes of an Asian hornet.

Contact Us

Copyright © 2002 - Chinese Academy of Sciences