Brief Introduction Bingxin Zhou obtained her Ph.D degree under the supervision of Prof. Junbin Gao and A/Prof. Minh Ngoc Tran in 2022 at the University of Sydney, Australia, titled with “Geometric Signal Processing with Graph Neural Networks”. Her current research focuses on developing spectral graph neural networks (GNNs) models and applying geometric deep learning methods for protein engineering, such directed evolution, antibody-antigen interaction, and de novo protein design. She has developed several useful graph neural networks including undecimated and decimated Framelet-based graph convolution, Grassmann graph pooling, spectral attention for learning dynamic graphs.

spectral graph neural networks hypergraph convolution neural networks geometric deep learning for protein engineering

Bingxin Zhou, Yuanhong Jiang, Yu Guang Wang, Jingwei Liang, Junbin Gao, Shirui Pan, and Xiaoqun Zhang. “Robust Graph Representation Learning for Local Corruption Recovery”, In The Web Conference, 2023. Xuebin Zheng, Bingxin Zhou, Yu Guang Wang, and Xiaosheng Zhuang, “Decimated Framelet System and Fast G-Framelet Transforms on Graph”, Journal of Machine Learning Research, 2022 Bingxin Zhou, Xinliang Liu, Yuehua Liu, Yunying Huang, Pietro Liò, and Yu Guang Wang. “Well-conditioned Spectral Transforms for Dynamic Graph Representation,” In Learning on Graph Conference, 2022. Bingxin Zhou, Xuebin Zheng, Yu Guang Wang, Ming Li, and Junbin Gao, “Embedding Graphs on Grassmann Manifold”, Neural Networks, 2022 Xuebin Zheng, Bingxin Zhou, Junbin Gao, Yu Guang Wang, Pietro Liò, Ming. Li, and Guito Montúfar, “How framelets enhance graph neural networks”, In International Conference on Machine Learning, 2021 Bingxin Zhou, Junbin Gao, Minh Nog Tran, and Richard Gerlach, “Manifold optimization Assisted Gaussian Variational Approximation”, Journal of Computation and Graphical Statistics, 2021