B. Wu MSc (Boqian)

PhD Candidate
EEMCS-CS-DMB
b.wu@utwente.nl
+31534898909
Business card

Boqian is a first-year Ph.D. student at the University of Twente in the Data Management & Biometrics (DMB) group. During her Ph.D., she is focusing on sparse neural networks, specifically the theoretical aspects of such networks. Her goal is to uncover the mechanisms that underlie the practical effectiveness of sparse neural networks.

Expertise

  • Computer Science

    • Classification Learning
    • Image Segmentation
    • Models
    • Online Portfolio
    • Receptive Field
    • Vision Transformer

  • Economics, Econometrics and Finance

    • Mean Reversion
    • Portfolio Selection

Organisations

Dynamic sparse training algorithms have shown promise in achieving high performance while reducing resource costs, making them an attractive option in machine learning. However, despite their potential, the theoretical properties of dynamic sparse training remain largely unexplored. My research aims to fill this knowledge gap by investigating the theoretical properties of sparse training models. As a result, guidelines will be developed for applying dynamic sparse training to real-world problems.

Publications

2023
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation. ArXiv.org. Wu, B., Xiao, Q., Liu, S., Yin, L., Pechenizkiy, M., Mocanu, D. C., Keulen, M. V. & Mocanu, E.https://doi.org/10.48550/arXiv.2312.04727Weighted Multivariate Mean Reversion for Online Portfolio SelectionIn Machine Learning and Knowledge Discovery in Databases: Research Track: European Conference, ECML PKDD 2023, Turin, Italy, September 18–22, 2023, Proceedings, Part V (pp. 255-270). Wu, B., Lyu, B. & Gu, J.https://doi.org/10.1007/978-3-031-43424-2_16More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsityIn The Eleventh International Conference on Learning Representations (ICLR 2023). OpenReview. Liu, S., Chen, T., Chen, X., Chen, X., Xiao, Q., Wu, B., Pechenizkiy, M., Mocanu, D. C. & Wang, Z.https://arxiv.org/abs/2207.03620Dynamic Sparse Network for Time Series Classification: Learning What to “See”. Xiao, Q., Wu, B., Zhang, Y., Liu, S., Pechenizkiy, M., Mocanu, E. & Mocanu, D. C.https://drive.google.com/file/d/10pxPf2aWTdMumUba_8-7v_jEZ3-K_uV3/viewCan Less Yield More? Insights into Truly Sparse Training. Xiao, Q., Wu, B., Yin, L., van Keulen, M. & Pechenizkiy, M.https://drive.google.com/file/d/1kbWZ9ejU9XvtOMRtAcVYmcoRCDIWj3zy/view
2022
Dynamic Sparse Network for Time Series Classification: Learning What to "see''. ArXiv.org. Xiao, Q., Wu, B., Zhang, Y., Liu, S., Pechenizkiy, M., Mocanu, E. & Mocanu, D. C.https://doi.org/10.48550/arXiv.2212.09840Dynamic Sparse Network for Time Series Classification: Learning What to “See”. Xiao, Q., Wu, B., Zhang, Y., Liu, S., Pechenizkiy, M., Mocanu, E. & Mocanu, D. C.https://openreview.net/forum?id=ZxOO5jfqSYwMore ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity. ArXiv.org. Liu, S., Chen, T., Chen, X., Chen, X., Xiao, Q., Wu, B., Kärkkäinen, T., Pechenizkiy, M., Mocanu, D. & Wang, Z.https://doi.org/10.48550/arXiv.2207.03620

Research profiles

Scan the QR code or
Download vCard