个人简介

我是西南财经大学统计与数据科学学院统计研究中心的教授。我的研究兴趣涵盖图学习与智能体推理，在医学科学和经济学领域有广泛应用。我同时是一家电力交易公司的联合创始人并担任首席技术官（CTO）。

🔥🔥 最新动态

• 2026.5: 🎉🎉 一篇论文被 BMC Psychiatry 接收。
• 2026.2: 🎉🎉 一篇论文发表在 npj Digital Medicine。
• 2026.1: 🎉🎉 一篇论文发表在 Frontiers in Oncology。

📐 教学经历

本学期我将讲授最优化理论 II。

授课课程：

🔬 研究方向

医学人工智能

arXiv 自闭症谱系障碍诊断与致病分析

魏璐

项目

• 自闭症谱系障碍（ASD）是一种复杂的神经发育疾病，显著影响社交能力，并以非典型、有限或重复的语言行为为特征。我们的研究聚焦于利用多模态脑影像数据结合图神经网络（GNN）进行ASD诊断，具体包括弥散张量成像（DTI）、结构磁共振成像（sMRI）和功能磁共振成像（fMRI）。此外，我们的目标是识别与ASD相关的脑网络中的致病性功能区域。

KDD 2025 机器学习用于调强放疗

刘斌*, 刘宇, 李智乾, 肖江河, 林华珍, 尹国圣

项目

• 我们设计了一种功能性深度强化学习算法用于自动放疗计划制定，充分考虑了放疗的复杂场景，其性能已接近满足临床要求。

经济人工智能

IJCAI 2023 利用图神经网络分析产业链

刘斌, 何久俊, 李自远, 黄晓阳, 张翔, 尹国圣

项目

• 产业链的数字化发展吸引了研究人员和政策制定者的越来越多的关注。关键问题之一是产业链效率如何受到外部因素（如宏观经济政策、政府监管或货币政策、国际政治因素等）和内部因素（如微观经济驱动因素等）的影响。在本项目中，我们利用图神经网络对产业链发展进行定量分析。

📝 发表论文

预印本

• Chunhong Ye, Bin Liu*. Exploring Asset Pricing Through Industrial Chain Dynamics: Insights from Graph Machine Learning. SSRN Electronic Journal (2025)

• Lu Wei, Yi Huang, Guosheng Yin, Fode Zhang, Manxue Zhang, Bin Liu*. Diagnosis and Pathogenic Analysis of Autism Spectrum Disorder Using Fused Brain Connection Graph. arXiv preprint arXiv:2410.07138 (2024).
• Ling Xiang, Quan Hu, Xiang Zhang, Wei Lan, Bin Liu*. Graph Neural Poisson Models for Supply Chain Relationship Forecasting. arXiv preprint arXiv:2508.12044 (2025).
• Yuedi Zhang, Zhixiang Xia, Guosheng Yin, Bin Liu*. Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Images. arXiv preprint arXiv:2509.11034 (2025)

会议论文

• Bin Liu, Yu Liu, Zhiqian Li, Jianghe Xiao, Huazhen Lin, Guosheng Yin. Automatic radiotherapy treatment planning with deep functional reinforcement learning. KDD, 2025, Toronto, ON, Canada, pp. 2426-2435.
• Zhizhong Tan, Min Hu, Bin Liu*, Guosheng Yin. Futures Quantitative Investment with Heterogeneous Continual Graph Neural Networks. ICDM, 2024, Abu Dhabi, UAE, pp. 851-856
• Jinjin Li, Bin Liu*, Chengyan Liu, Hongli Zhang. Predicting Housing Transaction with Common Covariance GNNs. IJCAI, 2024, Jeju, Korea, pp. 7323-7330.
• Jiujun He, Bin Liu, Guosheng Yin. Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling. AAAI, 2024, Vancouver, Canada, pp. 12385-12393.
• Bin Liu, Jiujun He, Ziyuan Li, Xiaoyang Huang, Xiang Zhang, Guosheng Yin. Interpret ESG Rating’s Impact on the Industrial Chain Using Graph Neural Networks. IJCAI, 2023, Macao, China, pp. 6076-6084.
• Lu Wei, Bin Liu*, Jiujun He, Manxue Zhang, Yi Huang. Autistic Spectrum Disorders Diagnose with Graph Neural Networks. ACM Multimedia, 2023, Ottawa, Canada, pp. 8819–8827.
• Zhuo Tan, Bin Liu*, Guosheng Yin. Asymmetric Self-Supervised Graph Neural Networks. IEEE International Conference on Big Data, Osaka, Japan, 2022, pp. 1369-1376.
• Jiujun He, Bin Liu, Xuan Yang. Non-local Patch Mixup for Unsupervised Domain Adaptation. IEEE International Conference on Data Mining (ICDM), Orlando, FL, USA, 2022, pp. 969-974.
• Bin Liu, Wang Liang, Yin Guosheng. Learning distributed sentence vectors with bi-directional 3D convolutions. The 28th International Conference on Computational Linguistics(COLING), Barcelona, Spain, 2020, pp. 6820–6830.
• Bin Liu, Xiaoxue Gao, Mengshuang He, Lin Liu, Guosheng Yin. A Fast Online COVID-19 Diagnostic System with Chest CT Scans. The 26TH ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Health Day), 2020, Virtual Conference. The online diagnosis system: https://www.covidct.cn/
• Bin Liu, Guosheng Yin. Chinese document classification with bi-directional convolutional language model. The 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Xi’an, China, 2020, pp. 1785–1788.
• Bin Liu, Zenglin Xu, Bo Dai, Haoli Bai, Xianghong Fang, Yazhou Ren, Shandian Zhe. Learning from semantically dependent multi-tasks. International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA, 2017, pp. 3498-3505.
• Haoli Bai, Zenglin Xu, Bin Liu, Yingming Li. Hierarchical probabilistic matrix factorization with network topology for multi-relational social network. Proceedings of The 8th Asian Conference on Machine Learning, PMLR 63:270-285, 2016.
• Bin Liu, Chao Song, Nianbo Liu. Distinguishing uncertain objects with multiple features for crowdsensing. IEEE Global Communications Conference, Austin, TX, USA, 2014, pp. 2751-2756.

期刊论文

• Tingting Luo, Jie Zhang, Manxue Zhang, Lei Li, Shengnan Zhao, Zhaozhi Yang, Yuchu Jiang, Bin Liu*, Yi Huang*. Age-related individual-specific subspace of autism spectrum disorder based on common orthogonal basis extraction algorithm improves the accuracy of clinical symptoms prediction. BMC Psychiatry, 2026.
• Zhang Mingyi, Bin Liu, Zhaojuan Qin, Yuedi Zhang, Zhiqian Li, Ruizhi Liu, Zhixiang Xia, Qiongxian Long, Jia Xu, Xiaoli Mou, Liansha Tang, Hongshuai Li, Wenjun Meng, Ai Zheng, Yangmei Shen, Jiyan Liu. Distinction between primary and metastatic mucinous ovarian carcinoma from histopathology images using deep learning. npj Digital Medicine, 2026.
• Zhang Mingyi, Xia Zhixiang, Liu Ruizhi, Qin Zhaojuan, Li Hongshuai, Xu Jia, Long Qiongxian, Shen Yangmei, *Liu Bin, Liu Jiyan Histopathology images-based deep learning prediction of prognosis in primary mucinous ovarian carcinoma. Frontiers in Oncology, vol. 16, 2026.
• Bin Liu, Li Haolong, Linshuang Kang. Tangency Portfolios Using Graph Neural Networks. Neural Networks, vol. 193, 108043, 2025, https://doi.org/10.1016/j.neunet.2025.108043
• Zhizhong Tan, Siyang Liu, Qiang Liu, Min Hu, Xiang Zhang, Wenyong Wang, Bin Liu*. Modeling ESG-driven industrial value chain dynamics using directed graph neural networks. Financial Innovation, vol. 11, 113, 2025, http://dx.doi.org/10.1186/s40854-025-00783-y
• Min Hu, Zhizhong Tan, Bin Liu*, and Guosheng Yin. Graph Portfolio: High-Frequency Factor Predictors via Heterogeneous Continual GNNs. IEEE Transactions on Knowledge and Data Engineering, vol. 37, no. 7, pp. 4104-4116, July 2025, doi: 10.1109/TKDE.2025.3566111.
• Min Hu, Bin Liu*, Guosheng Yin. Multi-Site and Multi-Pollutant Air Quality Data Modeling. Sustainability, vol. 16(1), 165. 2024.
• Bin Liu, Guosheng Yin. Graphmax for Text Generation. Journal of Artificial Intelligence Research, vol. 78, pp.823-848, Nov. 2023.
• Zhuo Tan, Yifan Zhu, Bin Liu*. Learning spatial-temporal feature with graph product. Signal Processing, 210 (2023): 109062.
• Shaogao Lv, Linsen Wei, Qian Zhang, Bin Liu, Zenglin Xu. “Improved Inference for Imputation-Based Semisupervised Learning Under Misspecified Setting”, IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 11, pp. 6346-6359, Nov. 2022.
• Liyuan Zheng, Yajie Hu, Bin Liu*, and Wei Deng. “Learning robust word representation over a semantic manifold.” Knowledge-Based Systems, 192 (2020): 105358.
• Zenglin Xu, Bin Liu*, Shandian Zhe, Haoli Bai, Zihan Wang, Jennifer Neville. Variational random function model for network modeling, IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 1, pp. 318-324, Jan. 2019.
• Bin Liu, Lirong He, Yingming Li, Shandian Zhe, Zenglin Xu. NeuralCP: Bayesian Multiway Data Analysis with Neural Tensor Decomposition, Cognitive Computation, 10, pp.1051–1061, 2018.
• He Lirong, Bin Liu, Guangxi Li, Yongpan Sheng, Yafang Wang, and Zenglin Xu. [Knowledge base completion by variational bayesian neural tensor decomposition], Cognitive Computation, 10 (2018): 1075-1084.
• Bin Liu, Yingming Li, Zenglin Xu. Manifold regularized matrix completion for multi-label learning with ADMM. Neural Networks, vol. 101, pp. 57-67, 2018.
• Bin Liu, Zenglin Xu, Shuang Wu, Fei Wang. Manifold regularized matrix completion for multilabel classification. Pattern Recognition Letters, Vol. 80, pp. 58-63, 2016.

🎖 荣誉与奖项

• 2016.10 ACML 2016 最佳论文 runner up。
• 2014.07 GlobeCom 2014 最佳论文候选。

🎓 教育背景

• 2013.09 - 2017.12, 电子科技大学，计算机科学博士。
• 2008.09 - 2011.06, 电子科技大学，计算机科学硕士。
• 2004.09 - 2008.06, 辽宁工业大学，计算数学学士。

🏫 访问经历

• 2024.7 - 2024.9, 香港大学，访问学者。
• 2023.11 - 2023.12, 伦敦帝国理工学院，访问学者。
• 2016.6 - 2017.6, 不列颠哥伦比亚大学，访问学生。

💻 工作经历

• 2018.04 - 至今, 西南财经大学统计学院，副教授，中国成都。
• 2025.03 - 2025.09, 香港大学计算与数据科学学院（HKUCDS），研究助理，中国香港。
• 2018.09 - 2020.09, 香港大学统计与精算学系，博士后，中国香港。

💬 学术报告

• 2024.07, 利用图机器学习解释外部冲击如何影响产业链，第七届计量经济学与统计学国际会议（EcoSta 2024），北京。
• 2023.08, 利用共现统计信息定制个人大规模语言模型，首届机器学习与统计会议，华东师范大学，上海。