Distributionally Robust Semi-Supervised Learning for People-Centric Sensing


  • Kaixuan Chen University of New South Wales
  • Lina Yao University of New South Wales
  • Dalin Zhang University of New South Wales
  • Xiaojun Chang Monash University
  • Guodong Long University of Technology Sydney
  • Sen Wang Griffith University




Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, humangenerated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biological conditions and behavior patterns of humans. To address this problem, we propose a generic distributionally robust model for semi-supervised learning on distributionally shifted data. Considering both the discrepancy and the consistency between the labeled data and the unlabeled data, we learn the latent features that reduce person-specific discrepancy and preserve task-specific consistency. We evaluate our model in a variety of people-centric recognition tasks on real-world datasets, including intention recognition, activity recognition, muscular movement recognition and gesture recognition. The experiment results demonstrate that the proposed model outperforms the state-of-the-art methods.




How to Cite

Chen, K., Yao, L., Zhang, D., Chang, X., Long, G., & Wang, S. (2019). Distributionally Robust Semi-Supervised Learning for People-Centric Sensing. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3321-3328. https://doi.org/10.1609/aaai.v33i01.33013321



AAAI Technical Track: Machine Learning