当前位置: X-MOL首页全球导师 国内导师 › 张浩

个人简介

副研究员,博导,目前任职于计算学部物联网与泛在智能研究中心和智慧农场技术与系统全国重点实验室,研究方向包括人工智能应用(气象预测,智慧农业),联邦学习,边缘计算等。 教育经历 2009~2014 中国科学技术大学 博士 2005~2009 中国科学技术大学 学士 工作经历 哈尔滨工业大学 博士生导师 2023.06 哈尔滨工业大学 硕士生导师 2023.04 哈尔滨工业大学 准聘副研究员 2020.07至今 华为南京研究所 高级工程师 2017~2020 中国电子科技集团公司第二十八研究所 工程师 2014~2017

研究领域

人工智能应用 基于人工智能的气象预测(多模态序列预测,多模态超分辨率) 气象预测具有巨大的社会价值,作为一种基础应用可以指导各行各业的生产生活(如农业,交通,物流等)。精准的气象预测是该领域的主要目标。然而,传统的数值计算方法的发展已经到达一定的瓶颈。近年来,随着人工智能技术的发展和丰富的气象数据储备,为人工智能方法解决气象预测问题提供了良好的机遇,受到了国家的高度重视和众多机构的关注。我们通过将人工智能方法引入气象领域,从计算机科学的角度重新思考气象预测问题,通过对高时空分辨率的短临,短期天气预测进行深入研究,克服传统天气预测面临的困难。 智慧农业 农机调度规划(强化学习) 大面积农田作业(如耕地,除草,喷药等)需要使用多台农机共同执行。同时,由于成本、农机特点等因素决定了协同农机是异构的(大农机,小农机,无人机等),为此需要根据不同农机的特点进行作业路径规划。系统运行时,根据环境信息和控制指令的变化执行相应的行为方式,以实现在油耗、能耗、网络环境和自然环境受限的情况下,异构农业机器人群体智能的高效协作。 todo 联邦学习(分布式深度学习训练) 传统的AI训练通常需要将数据集中进行训练,然而由于“数据孤岛”带来的隐私问题,以及物联网的发展带来的数据弥散问题,使得联邦学习这种分布式训练方式成为了一种新的训练范式,受到目前学术界和工业界的广泛关注。然而,联邦学习仍然存在诸多挑战,包括数据异质性问题带来的性能降低,大的通信开销,公平性问题,设备异质性问题,安全性问题等等。我们通过对联邦学习的深入研究,从性能、公平性、开销等多方面考虑,旨在提升联邦学习的应用潜力,实现真正的分布式“即插即用”联邦学习。

近期论文

查看导师新发文章 (温馨提示:请注意重名现象,建议点开原文通过作者单位确认)

专著 Hao Zhang , Yonggang Wen, Haiyong Xie, Nenghai Yu. Distributed hash table: Theory, platforms and applications. Springer. 2013. 期刊论文 Hao Zhang, Qingying HouTingtingWu, Siyao Cheng, Jie Liu. Data Augmentation Based Federated Learning[J]. IEEE Internet of Things Journal, 2023. [paper].(SCI一区) Zhifeng Ma, Hao Zhang*, Jie Liu. MS-LSTM: Exploring Spatiotemporal Multiscale Representations in Video Prediction Domain[J]. Applied Soft Computing. 2023. [paper] (SCI二区) Hao Zhang, TingtingWu, Siyao Cheng, Jie Liu. CC-FedAvg: Computationally Customized Federated Averaging[J]. IEEE Internet of Things Journal, 2023. [paper] (SCI一区) Yinlong Li, Siyao Cheng, Hao Zhang, Jie Liu. Dynamic adaptive workload offloading strategy in mobile edge computing networks[J]. Computer Networks, 2023. [paper] (CCF-B) Tingting Wu, Xiao Ding, Hao Zhang, Jinglong Gao, Minji Tang, Li Du, Bing Qin, Ting Liu. DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination[J]. IEEE Transactions on Multimedia, 2023. [paper] (SCI一区) Hao Zhang, Tingting Wu, Zhifeng Ma, Feng Li, Jie Liu. Dynamic layer-wise sparsification for distributed deep learning[J]. Future Generation Computer Systems, 2023, 147:1-15. [paper](SCI二区) Zhifeng Ma, Hao Zhang*, Jie Liu. MM-RNN: A Multimodal RNN for Precipitation Nowcasting[J]. IEEE Transactions on Geoscience and Remote Sensing. 2023, 61: 1-14. [paper] (SCI一区,CCF-B) 马志峰,张浩*,刘劼. 基于深度学习的端临降水预报综述[J]. 计算机工程与科学. 2023. (CCF T2推荐中文期刊,已录用) Hao Zhang, TingtingWu, Siyao Cheng, Jie Liu. FedCos: A Scene-adaptive Enhancement for Federated Learning[J]. IEEE Internet of Things Journal, 2023, 10(5): 4545 - 4556. [paper][code](SCI一区) Zhifeng Ma, Hao Zhang*, Jie Liu. PrecipLSTM: A Meteorological Spatiotemporal LSTM for Precipitation Nowcasting[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-8. [paper] (SCI一区,CCF-B) Zhifeng Ma, Hao Zhang*, Jie Liu. Focal Frame Loss: A Simple but Effective Loss for Precipitation Nowcasting[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 6781-6788. [paper](JCR一区) Hao Zhang, Nenghai Yu, Yonggang Wen. Mobile cloud computing based privacy protection in location‐based information survey applications[J]. Security and Communication Networks, 2015, 8(6): 1006-1025. Hao Zhang, Nenghai Yu, Yonggang Wen, Weiming Zhang. Towards optimal noise distribution for privacy preserving in data aggregation[J]. Computers & security, 2014, 45: 210-230. [paper](CCF-B) Hao Zhang, Nenghai Yu, Honggang Hu. The optimal noise distribution for privacy preserving in mobile aggregation applications[J]. International Journal of Distributed Sensor Networks, 2014, 10(2): 678098. 会议论文 Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu. NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing[C]//Findings of the Association for Computational Linguistics: ACL 2023. [paper][dataset][code] Bolong Liu,Hao Zhang, Jie Liu, and Qiang Wang. ACIGS: An automated large-scale crops image generation system based on large visual language multi-modal models. Workshop on Sensing, Communication and Networking for Smart Agriculture (AgriSECON 2023). 7-13.2023. Hao Zhang, Tingting Wu, Siyao Cheng, Jie Liu. Aperiodic Local SGD: Beyond Local SGD[C]//Proceedings of the 51st International Conference on Parallel Processing. 2022: 1-10.[paper] (CCF-B) Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu. STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022: 7587-7598. [paper] (CCF-B) Zhifeng Ma, Shuaibo Li, Hao Zhang, Jie Liu. Hierarchical convolutional recurrent neural network for Chinese text classification[C]//Second International Conference on Sensors and Information Technology (ICSI 2022). SPIE, 2022, 12248: 213-219. Hao Zhang, Yonggang Wen, Nenghai Yu, Xinwen Zhang. Privacy-preserving computation for location-based information survey via mobile cloud computing[C]//2013 IEEE/CIC International Conference on Communications in China (ICCC). IEEE, 2013: 100-105.

学术兼职

IEEE Internet of Things Journal,IEEE Transactions on Industrial Informatics等期刊审稿人 The IEEE International Conference on Multimedia & Expo (ICME) 2020, 2021任meta reviewer IEA/AIE 2023 PC成员 全国信标委物联网分技术委员会专家 CCF物联网专委会执行委员

推荐链接
down
wechat
bug