梁新彦 - 计算机与信息技术学院（大数据学院）

梁新彦，博士，副教授，山西大学“文瀛青年学者”人才计划（首批）。 2022年6月博士毕业于山西大学计算机科学与技术专业，博士期间曾于2017-2018年赴香港大学从事研究助理的工作。2022年8月加入山西大学大数据科学与产业研究院。研究方向：多模态机器学习、信号处理及其在微波原子探测方面的应用。近年来在IEEE TPAMI、IEEE TEVC、IEEE TCSVT、PR、ICLR、AAAI、IJCAI、ACM MM等国内外重要学术期刊、会议发表论文30余篇。主持军科委JCJQ重大类项目课题、基金委重大项目子课题、基金委青年项目、山西省重大项目课题等多项。担任Nature Communications、IEEE TEVC、NeurIPS、ICML、ICLR、CVPR、ICCV等多个国际期刊、会议的审稿人。曾获山西省优秀博士论文奖。

会议论文：

[1] Xinyan Liang, Pinhan Fu, Yuhua Qian, Qian Guo, Guoqing Liu. Trusted multi-view classification via evolutionary multi-view fusion. In: Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025. (机器学习三大顶会之一)

[2] Bingbing Jiang, Chenglong Zhang, Xinyan Liang, Peng Zhou, Jie Yang, Xingyu Wu, Junyi Guan, Weiping Ding, Weiguo Sheng. Collaborative similarity fusion and consistency recovery for incomplete multi-view clustering. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI-25), 2025. (CCF-A)

[3] Zhongli Wang, Jie Yang, Junyi Guan, Chenglong Zhang, Xinyan Liang, Bingbing Jiang, Weiguo Sheng. Enhanced denesity peak clustering for high-dimensional data. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI-25), 2025. (CCF-A)

[4] Xinyan Liang, Pinhan Fu, Qian Guo, Keyin Zheng, Yuhua Qian. DC-NAS: Divide-and-Conquer Neural Architecture Search for Multi-Modal Classification. Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), 2024, 38(12): 13754-13762. (CCF-A)

[5] Zhangqi Jiang, Tingjin Luo, Xinyan Liang. Deep Incomplete Multi-View Learning Network with Insufficient Label Information. Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), 2024, 38(11): 12919-12927. (CCF-A)

[6] Pinhan Fu, Xinyan Liang, Tingjin Luo, Qian Guo, Yayu Zhang, Yuhua Qian. Core-Structures-Guided Multi-Modal Classification Neural Architecture Search, The 33rd International Joint Conference on Artificial Intelligence (IJCAI-24), 2024: 3980-3988. (CCF-A)

[7] Chenglong Zhang, Yang Fang, Xinyan Liang, Han Zhang, Peng Zhou, Xingyu Wu, Jie Yang, Bingbing Jiang, Weiguo Sheng. Efficient Multi-view Unsupervised Feature Selection with Adaptive Structure Learning and Inference. The 33rd International Joint Conference on Artificial Intelligence (IJCAI-24), 2024: 5443-5452. (CCF-A)

[8] Qian Guo, Xinyan Liang, Yuhua Qian, Zhihua Cui, Jie Wen. A progressive skip reasoning fusion method for multi-modal classification. The 32nd ACM MULTIMEDIA 2024 (ACM MM-24), 2024: 429-437. (CCF-A, Oral 录用率3.97%)

[9] Pinhan Fu, Xinyan Liang, Yuhua Qian, Qian Guo, Zhifang Wei, Wen Li. CoMO-NAS: Core-structures-guided multi-objective neural architecture search for multi-modal classification. The 32nd ACM MULTIMEDIA 2024 (ACM MM-24), 2024: 9126-9135. (CCF-A)

[10] Chenglong Zhang, Xinyan Liang, Peng Zhou, Zhaolong Ling, Yingwei Zhang, Xingyu Wu, Weiguo Sheng, Bingbing Jiang. Scalable multi-view unsupervised feature selection with structure learning and fusion. The 32nd ACM MULTIMEDIA 2024 (ACM MM-24), 2024: 5479-5488. (CCF-A)

期刊论文：

[1] Xinyan Liang, Yuhua Qian, Qian Guo, Honghong Cheng, Jiye Liang. AF: An association-based fusion method for multi-modal classification. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2022, 44(12): 9236-9254. (CCF-A 类, SCI-1区Top)

[2] Xinyan Liang, Qian Guo, Yuhua Qian, Weiping Ding, Qingfu Zhang. Evolutionary deep fusion method and its application in chemical structure recognition. IEEE Transactions on Evolutionary Computation (IEEE TEVC), 2021, 25(5): 883-893. (SCI-1区Top)

[3] Pinhan Fu, Xinyan Liang, Yuhua Qian, Qian Guo, Yayu Zhang, Qin Huang. Multi-scale features are effective for multi-modal classification: An architecture search viewpoint. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025, 35(2): 1070-1083. (SCI-1区Top)

[4] Xinyan Liang, Yuhua Qian, Qian Guo, Keyin Zheng. A data representation method using distance correlation. Frontiers of Computer Science, 2025, 19(1): 191303. (CCF-B)

[5] Yayu Zhang, Yuhua Qian, Guoshuai Ma, Xinyan Liang, Guoqing Liu, Qingfu Zhang, Ke Tang. ESSR: Evolving sparse sharing representation for multi-task learning. IEEE Transactions on Evolutionary Computation (IEEE TEVC), 2024, 28(3): 748-762. (SCI-1区Top)

[6] Yuhua Qian, Xinyan Liang, Qi Wang, Jiye Liang, Bing Liu, Andrzej Skowron, Yiyu Yao, Jianmin Ma, Chuangyin Dang. Local rough set: A solution to rough data analysis in big data. International Journal of Approximate Reasoning (IJAR), 2018, 97: 38-63. (CCF-B)

[7] Yuhua Qian, Xinyan Liang, Guoping Lin, Qian Guo, Jiye Liang. Local multigranulation decision-theoretic rough sets. International Journal of Approximate Reasoning (IJAR), 2017, 82: 119-137. (CCF-B)

[8] Qi Wang, Yuhua Qian, Xinyan Liang, Qian Guo, Jiye Liang. Local neighborhood rough set. Knowledge-Based Systems (KBS), 2018, 153: 53-64. (SCI-1区)

[9] Qian Guo, Yuhua Qian, Xinyan Liang. GLRM: Logical pattern mining in the case of inconsistent data distribution based on multigranulation strategy. International Journal of Approximate Reasoning (IJAR), 2022, 143: 78-101. (CCF-B)

[10] Qian Guo, Yuhua Qian, Xinyan Liang, Yanhong She, Deyu Li, Jiye Liang. Logic could be learned from images. International Journal of Machine Learning and Cybernetics (JMLC), 2021, 12: 3397-3414. (SCI-2区)

[11] Qian Guo, Yuhua Qian, Xinyan Liang, Junyu Chen, Honghong Cheng. Multi-granulation multi-scale relation network for abstract reasoning. International Journal of Machine Learning and Cybernetics (JMLC), 2022, 13: 1751-1762. (SCI-2区)

[12] Yan Chen, Qian Guo, Xinyan Liang, Jiang Wang, Yuhua Qian. Environmental sound classification with dilated convolutions. Applied Acoustics, 2019, 148: 123-132. (SCI-2区)

[13] Bassoma Diallo, Jie Hu, Tianrui Li, Ghufran Ahmad Khan, Xinyan Liang, Hongjun Wang. Auto-attention Mechanism for Multi-view Deep Embedding Clustering. Pattern Recognition (PR), 2023(143): 109764. (SCI-1区)

[14] Qian Liu, Xia Zhang, Xinyan Liang, Yuhua Qian, Shanshan Yao, AWLloss: Speaker Verification Based on the Quality and Difficulty of Speech. IEEE Signal Processing Letters (SPL), 2023(30): 1337-1341

[15] 梁新彦, 钱宇华, 郭倩, 黄琴. 多粒度融合驱动的超多视图分类方法. 计算机研究与发展, 2022, 59(8): 1653-1667. (CCF-A)

[16] 张璐, 曹峰, 梁新彦, 钱宇华. 基于关联特征传播的跨模态检索. 计算机研究与发展, 2022, 59(9): 1993-2002. (CCF-A)

[1] 国家自然科学基金重大项目, 智能原子微波探测理论与方法(T2495250), 2025-01 至 2029-12, 1500万, 子课题负责人

[2] 国家自然科学基金青年项目, 特征关联语义下的多模态表征融合机理与方法研究(62306171), 2024-01 至 2026-12, 30万, 主持

[3] 山西省科技厅, 山西省科技重大专项计划“揭榜挂帅”项目课题, 面向复杂电磁大数据的多模态知识挖掘技术, 2023-01 至 2026-01, 140万元, 在研, 主持

[4] 科技部科技创新2030--“新一代人工智能”重大项目, 基于多智能体超图的自主决策, 学习理论与动态调控策略研究, 2022-01-01至2024-12-31, 参与