YWYukun Wang

Yukun Wang

*This is an algorithmically generated author record based on publicly available information.

Yukun Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Party

    by Yimin Huang, Wanwan Wang, Xingying Zhao, Yukun Wang, Xinyu Feng, Hao He, Ming Yao

    Federated learning (FL) is a machine learning setting which allows multiple participants collaboratively to train a model under the orchestration of a server without disclosing their local data. Vertical federated learning (VFL) is a special structure in FL. It handles the situation where participants have the same ID space but different feature spaces. In order to guarantee the security and privacy of the local data of each participant, homomorphic encryption (HE) is often used to transmit intermediate parameters or data during the training process. In most VFL frameworks, a trusted third-party server is necessary because the plaintexts of the parameters need to be revealed for the computation. However, it is hard to find such a credible entity in the real world. Existing methods for solving this problem are either communication-intensive or unsuitable for multi-party scenarios. By combining secret sharing (SS) and HE, we propose a novel VFL framework without any trusted third parties called EFMVFL. It allows intermediate parameters to be transmitted among multiple parties without revealing the plaintexts. EFMVFL is applicable to generalized linear models (GLMs) and supports flexible expansion to multiple participants. Extensive experiments under Logistic Regression and Poisson Regression show that our framework is outstanding in communication (reduced by 3.2×– 6.8×) and efficiency (accelerated by 1.6×– 3.1×).


  • Open Access

    Deep Learning-Based Image Processing for Whitecaps on the Ocean Surface

    by Yukun Wang, Yuji Sugihara, Xianting Zhao, Haruki Nakashima, Osama Eljamal

    Whitecaps generated by wave breaking on the ocean surface play an important role in the local interaction across the air-sea interface. Whitecap coverage is defined by the area of whitecaps per the unit ocean surface. It has been recognized as one of the most valuable physical quantities for describing the ocean surface fluxes such as the momentum, heat and carbon dioxide, so that the quantitative evaluation of whitecap coverage becomes significant from viewpoints of coastal and ocean engineering. In this study, a progressive high-precision whitecap extraction model is first built by using the algorithm of deep learning. Compared with a traditional whitecap extraction model based on threshold value, the algorithm is found to solve problems caused by illuminance condition and color change on the ocean surface, and effectively extracts fine whitecaps with complicated structures. Further, through comparisons with previous algorithms such as Automatic Whitecap Extraction (AWE), Iterative Between Class Variance (IBCV) and the whitecap extraction based on fixed threshold value, the present algorithm is demonstrated to be more accurate for identifying whitecaps, and it reduces the amount of evaluation load, and can effectively apply for changeable ocean conditions. The new whitecap extraction technology is used to determine whitecap coverage when shooting digital images under complicated sea surface conditions. Due to the progressive characteristics of this algorithm, it has not only a high precision processing effect on images taken by a fixed camera, but also has the potential to analyze accurately images from a non-fixed camera system, such as an observation ship equipped with camera system, unmanned aerial vehicle and so on.