Instilling Social to Physical: Co-Regularized Heterogeneous Transfer Learning

By Ying Wei, Yingke Zhu, Cyril Leung, Yangqiu Song, Qiang Yang. 2016

34 citations recorded by the source corpus.

Ubiquitous computing tasks, such as human activity recognition (HAR), are enabling a wide spectrum of applications, ranging from healthcare to environment monitoring. The success of a ubiquitous computing task relies on sufficient physical sensor data with groundtruth labels, which are always scarce due to the expensive annotating process. Meanwhile, social media platforms provide a lot of social or semantic context information. People share what they are doing and where they are frequently in the messages they post. This rich set of socially shared activities motivates us to transfer knowledge from social media to address the sparsity issue of labelled physical sensor data. In order to transfer the knowledge of social and semantic context, we propose a Co-Regularized Heterogeneous Transfer Learning (CoHTL) model, which builds a common semantic space derived from two heterogeneous domains. Our proposed method outperforms state-of-the-art methods on two ubiquitous computing tasks, namely human activity recognition and region function discovery.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Yu Zhang
3. Yu Zheng
4. Ying Wei
5. Vincent Wenchen Zheng
6. Bin Guo
7. Zhu Wang
8. Jing Li

In Electrical and Electronic Engineering

1. Yu Zhang
2. Qiang Yang
3. Yu Zheng
4. Vincent Wenchen Zheng
5. Dongrui Wu
6. Vladlen Koltun
7. Ozan Sener

Citations in the corpus

• Transfer Knowledge between Cities (2016, background): “This work and its follow-up [16], however, can only handle the case where both source and target domains contain single modality only.”
• CityTransfer (2018, background): “There have been recently a few studies that leverage transfer learning to address the no-training-data issue in the ubiquitous computing field [11,37,38,41].”
• Transferable Contextual Bandit for Cross-Domain Recommendation (2018, methodology): “We compare TCB with four representative baselines, including HTL (Wei et al. 2016), LinUCB (Li et al.”