姓名:徐华
职称:长聘副教授,博士生导师
电话:13810102923
邮件:xuhua@mail.tsinghua.edu.cn
教育背景
学士(计算机科学与技术),西安交通大学,中国,1998;
硕士(计算机应用技术),清华大学,中国,2000;
博士(计算机应用技术),清华大学,中国,2003.
研究领域
多模态智能信息处理,智能优化
研究概况
长期从事多模态智能信息处理、共融机器人智能控制等,研究方向是人工智能领域的智能优化调度和人机自然交互,在北京的国家信息科学与技术研究中心等研究平台上开展研究。近年来,完成国家科技重大专项课题3项、国家自然科学基金项目4项、国家973项目课题2项、国家863项目课题5项以及国际500强企业合作项目13项。曾受邀担任工业和信息化部重大科技项目03号的核心专家,担任“技术支撑经济2020”国家重点研发计划项目验收专家组组长,国家发展和改革委员会国家工业创新中心的咨询专家,Elsevier国际期刊Intell. Syst. Appl.的主编和Expert Syst. Appl.的副主编(第一四分位,SCI影响因子=8.665)。曾获国家科技进步二等奖,北京市科学技术一等奖,行业协会科技一等奖2次,省部级二、三等奖3次。获国家发明专利36项,软件著作权26项,著作3部教材、6部专著。贡献被引用于ACM Comput. Surv等顶级期刊,被国内外6位亚博安全有保障士和30多位IEEE院士引用。在机器人智能优化调度方面,提出了面向多目标优化调度的智能演化理论和多机器人协作的柔性作业车间调度(FJS)方法技术;机器人自然交互方面,研究并建立面向自然交互的情感分析与意图理解方法和开源平台,成为当前机器人智能系统领域进行交互情感感知和对话意图理解的有效方法。
成果链接
1) 研究组主页:https://thuiar.github.io/
2) 成果共享网址:https://github.com/thuiar
奖励与荣誉
中国仿真学会科学技术将 自然科学二等奖(2023)
中国物流与采购联合会科技发明奖 一等奖(2015)
北京市科学技术奖 二等奖(2014)
北京市科学技术奖 三等奖(2014)
中国物流与采购联合会科技进步奖 一等奖(2013)
重庆市科学技术奖 三等奖(2011)
PAKDD 2011最佳论文奖(2011)
国家科学技术进步奖 二等奖(2009)
北京市科学技术奖 一等奖(2008)
学术成果
Multimodal Emotion Analysis
[1]Mao H, Zhang B, Xu H, et al. Robust-MSA: Understanding the impact of modality noise on multimodal sentiment analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37(13): 16458-16460.
[2]Yuan Z, Liu Y, Xu H, et al. Noise Imitation Based Adversarial Training for Robust Multimodal Sentiment Analysis[J]. IEEE Transactions on Multimedia, 2023.
[3]Xu H, Yuan Z, Zhao K, et al. Gar-net: A graph attention reasoning network for conversation understanding[J]. Knowledge-Based Systems, 2022, 240: 108055.
[4]Yu W, Xu H. Co-attentive multi-task convolutional neural network for facial expression recognition[J]. Pattern Recognition, 2022, 123: 108401.
[5]Mao H, Yuan Z, Xu H, et al. M-sena: An integrated platform for multimodal sentiment analysis[J]. arXiv preprint arXiv:2203.12441, 2022.
[6]Mao H, Zhang B, Xu H, et al. An End-to-End Traditional Chinese Medicine Constitution Assessment System Based on Multimodal Clinical Feature Representation and Fusion[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(11): 13200-13202
[7]Liu Y, Yuan Z, Mao H, et al. Make Acoustic and Visual Cues Matter: CH-SIMS v2. 0 Dataset and AV-Mixup Consistent Module[C]//Proceedings of the 2022 International Conference on Multimodal Interaction. 2022: 247-258.
[8]Yuan Z, Li W, Xu H, et al. Transformer-based feature reconstruction network for robust multimodal sentiment analysis[C]//Proceedings of the 29th ACM International Conference on Multimedia. 2021: 4400-4407.
[9]Yu W, Xu H, Yuan Z, et al. Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(12): 10790-10797.
[10]Li H, Xu H. Deep reinforcement learning for robust emotional classification in facial expression recognition[J]. Knowledge-Based Systems, 2020, 204: 106172.
[11]Yang K, Xu H, Gao K. Cm-bert: Cross-modal bert for text-audio sentiment analysis[C]//Proceedings of the 28th ACM international conference on multimedia. 2020: 521-528.
[12]Yu W, Xu H, Meng F, et al. Ch-sims: A chinese multimodal sentiment analysis dataset with fine-grained annotation of modality[C]//Proceedings of the 58th annual meeting of the association for computational linguistics. 2020: 3718-3727.
[13]Xu Y, Xu H, Zou J. Hgfm: A hierarchical grained and feature model for acoustic emotion recognition[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020: 6499-6503.
[14]Cao Y, Xu H. Satnet: Symmetric adversarial transfer network based on two-level alignment strategy towards cross-domain sentiment classification (student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13763-13764.
[15]Wang X, Xu H, Sun X, et al. Combining fine-tuning with a feature-based approach for aspect extraction on reviews (student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13951-13952.
Multimodal Intent Understanding
[1]Zhou Q, Xu H, Li H, et al. Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition[J]. arXiv preprint arXiv:2312.14667, 2023.
[2]Zhang H, Xu H, Wang X, et al. A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery[J]. IEEE Transactions on Knowledge and Data Engineering, 2023.
[3]Zhang H, Xu H, Zhao S, et al. Learning discriminative representations and decision boundaries for open intent detection[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023.
[4]Zhang H, Xu H, Wang X, et al. Mintrec: A new dataset for multimodal intent recognition[C]//Proceedings of the 30th ACM International Conference on Multimedia. 2022: 1688-1697.
[5]Zhang H, Xu H, Lin T E, et al. Discovering new intents with deep aligned clustering[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35(16): 14365-14373.
[6]Zhang H, Xu H, Lin T E. Deep open intent classification with adaptive decision boundary[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35(16): 14374-14382.
[7]Zhang H, Li X, Xu H, et al. TEXTOIR: An integrated and visualized platform for text open intent recognition[J]. arXiv preprint arXiv:2110.15063, 2021.
[8]Lin T E, Xu H, Zhang H. Discovering new intents via constrained deep adaptive clustering with cluster refinement[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(05): 8360-8367.
[9]Lin T E, Xu H, Zhang H. Constrained self-supervised clustering for discovering new intents (student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13863-13864.
[10]Lin T E, Xu H. A post-processing method for detecting unknown intent of dialogue system via pre-trained deep neural network classifier[J]. Knowledge-Based Systems, 2019, 186: 104979.
[11]Lin T E, Xu H. Deep unknown intent detection with margin loss[J]. arXiv preprint arXiv:1906.00434, 2019.
Reading Comprehension Related to Question Answering
[1]Wu Z, Xu H. Trustworthy machine reading comprehension with conditional adversarial calibration[J]. Applied Intelligence, 2023, 53(11): 14298-14315.
[2]Wu Z, Fang J, Xu H, et al. An In-depth Interactive and Visualized Platform for Evaluating and Analyzing MRC Models[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022: 5044-5048.
[3]Wu Z, Xu H, Fang J, et al. Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation[J]. arXiv preprint arXiv:2208.05217, 2022.
[4]Wu Z, Xu H. Improving the robustness of machine reading comprehension model with hierarchical knowledge and auxiliary unanswerability prediction[J]. Knowledge-Based Systems, 2020, 203: 106075.
[5]Wu Z, Xu H. A Multi-Task Learning Machine Reading Comprehension Model for Noisy Document (Student Abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13963-13964.
Entity Recognition and Relation Extraction for Interactive Information
[1]Zhao K, Xu H, Yang J, et al. Consistent representation learning for continual relation extraction[J]. arXiv preprint arXiv:2203.02721, 2022.
[2]Zhao K, Xu H, Cheng Y, et al. Representation iterative fusion based on heterogeneous graph neural network for joint entity and relation extraction[J]. Knowledge-Based Systems, 2021, 219: 106888.
[3]Xie Y, Xu H, Li J, et al. Heterogeneous graph neural networks for noisy few-shot relation classification[J]. Knowledge-Based Systems, 2020, 194: 105548.
[4]Xie Y, Xu H, Yang C, et al. Multi-channel convolutional neural networks with adversarial training for few-shot relation classification (student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13967-13968.
Intelligent Evolutionary Algorithms
[1]Yuan Y, Ong Y S, Gupta A, et al. Objective reduction in many-objective optimization: evolutionary multiobjective approaches and comprehensive analysis[J]. IEEE Transactions on Evolutionary Computation, 2017, 22(2): 189-210.
[2] Yuan Y, Xu H, Wang B, et al. A new dominance relation-based evolutionary algorithm for many-objective optimization[J]. IEEE Transactions on Evolutionary Computation, 2015, 20(1): 16-37.
[3] Yuan Y, Ong Y S, Gupta A, et al. Evolutionary multitasking in permutation-based combinatorial optimization problems: Realization with TSP, QAP, LOP, and JSP[C]//2016 IEEE Region 10 Conference (TENCON). IEEE, 2016: 3157-3164.
[4] Yuan Y, Xu H, Wang B, et al. Balancing convergence and diversity in decomposition-based many-objective optimizers[J]. IEEE Transactions on Evolutionary Computation, 2015, 20(2): 180-198.
[5] Yuan Y, Xu H, Wang B. An experimental investigation of variation operators in reference-point based many-objective optimization[C]//Proceedings of the 2015 annual conference on genetic and evolutionary computation. 2015: 775-782.
[6] Yuan Y, Xu H, Wang B. An improved NSGA-III procedure for evolutionary many-objective optimization[C]//Proceedings of the 2014 annual conference on genetic and evolutionary computation. 2014: 661-668.
[7] Yuan Y, Xu H, Wang B. Evolutionary many-objective optimization using ensemble fitness ranking[C]//Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation. 2014: 669-676.
Flexible Job Shop Scheduling Problem Algorithm
[1] Multiobjective Flexible Job Shop Scheduling Using Memetic Algorithms[J]. IEEE Transactions on Automation Science and Engineering.
[2] Yuan Y, Xu H, Yang J. A hybrid harmony search algorithm for the flexible job shop scheduling problem[J]. Applied soft computing, 2013, 13(7): 3259-3272.
[3] Yuan Y, Xu H. Flexible job shop scheduling using hybrid differential evolution algorithms[J]. Computers & Industrial Engineering, 2013, 65(2): 246-260.
[4] Yuan Y, Xu H. An integrated search heuristic for large-scale flexible job shop scheduling problems[J]. Computers & Operations Research, 2013, 40(12): 2864-2877.
[5] Yuan Y, Xu H. A memetic algorithm for the multi-objective flexible job shop scheduling problem[C]//Proceedings of the 15th annual conference on Genetic and evolutionary computation. 2013: 559-566.
[6] Yuan Y, Xu H. HHS/LNS: an integrated search method for flexible job shop scheduling[C]//2012 IEEE Congress on Evolutionary Computation. IEEE, 2012: 1-8.
Learning classifiers
[1] Yang J, Xu H, Jia P. Effective search for genetic-based machine learning systems via estimation of distribution algorithms and embedded feature reduction techniques[J]. Neurocomputing, 2013, 113: 105-121.
[2] Xu H, Yang J, Jia P, et al. Effective structure learning for estimation of distribution algorithms via L1-regularized Bayesian networks[J]. International Journal of Advanced Robotic Systems, 2013, 10(1): 17.
[3] Yang J, Xu H, Jia P. Effective search for Pittsburgh learning classifier systems via estimation of distribution algorithms[J]. Information Sciences, 2012, 198: 100-117.
[4] Xu H, Wen Y, Wang J. A fast-convergence distributed support vector machine in small-scale strongly connected networks[J]. Frontiers of Electrical and Electronic Engineering, 2012, 7: 216-223.
[5] Wen Y, Xu H, Yang J. A heuristic-based hybrid genetic-variable neighborhood search algorithm for task scheduling in heterogeneous multiprocessor system[J]. Information Sciences, 2011, 181(3): 567-581.
[6] Yang J, Xu H, Pan L, et al. Task scheduling using Bayesian optimization algorithm for heterogeneous computing environments[J]. Applied Soft Computing, 2011, 11(4): 3297-3310.
[7] Wen Y, Xu H. A cooperative coevolution-based pittsburgh learning classifier system embedded with memetic feature selection[C]//2011 IEEE Congress of Evolutionary Computation (CEC). IEEE, 2011: 2415-2422.
[8] Wen Y, Xu H, Yang J. A heuristic-based hybrid genetic algorithm for heterogeneous multiprocessor scheduling[C]//Proceedings of the 12th annual conference on Genetic and evolutionary computation. 2010: 729-736.
[9] Yang J, Xu H, Cai Y, et al. Effective structure learning for EDA via L1-regularizedbayesian networks[C]//Proceedings of the 12th annual conference on Genetic and evolutionary computation. 2010: 327-334.
[10] Yang J, Xu H, Jia P. Task Scheduling for Heterogeneous Computing Based on Learning Classifier System[C]//2009 International Conference on Artificial Intelligence and Computational Intelligence. IEEE, 2009, 3: 370-374.
Bayesian Optimization
[1] Wang H, Xu H, Zhang Z. High-Dimensional Multi-Objective Bayesian Optimization With Block Coordinate Updates: Case Studies in Intelligent Transportation System[J]. IEEE Transactions on Intelligent Transportation Systems, 2023.
[2] Wang H, Xu H, Yuan Y. High-dimensional expensive multi-objective optimization via additive structure[J]. Intelligent Systems with Applications, 2022, 14: 200062.
[3] Wang H, Xu H, Yuan Y, et al. An adaptive batch Bayesian optimization approach for expensive multi-objective problems[J]. Information Sciences, 2022, 611: 446-463.
[4] Wang H, Xu H, Yuan Y, et al. Balancing exploration and exploitation in multiobjective batch bayesian optimization[C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2019: 237-238.
[5] Wang H, Xu H, Yuan Y, et al. Noisy multiobjective black-box optimization using Bayesian optimization[C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2019: 239-240.
Fast Large-Scale Optimization Algorithms
[1] Ye H, Xu H, Wang H, et al. GNN&GBDT-guided fast optimizing framework for large-scale integer programming[C]//International Conference on Machine Learning. PMLR, 2023: 39864-39878.
[2] Ye H, Wang H, Xu H, et al. Adaptive constraint partition based optimization framework for large-scale integer linear programming (student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37(13): 16376-16377.
[3] Chen L, Xu H, Wang Z, et al. Self-paced learning based graph convolutional neural network for mixed integer programming (student abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37(13): 16188-16189.
[4] Chen L, Xu H. MFENAS: multifactorial evolution for neural architecture search[C]//Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2022: 631-634.
[5] Chen L, Xu H. CORAL-DMOEA: Correlation Alignment-Based Information Transfer for Dynamic Multi-Objective Optimization (Student Abstract)[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2020, 34(10): 13765-13766.
Smart healthcare
[1] Xu H, Chen X, Qian P, et al. A two-stage segmentation of sublingual veins based on compact fully convolutional networks for Traditional Chinese Medicine images[J]. Health Information Science and Systems, 2023, 11(1): 19.
[2] Mao H, Zhang B, Xu H, et al. An End-to-End Traditional Chinese Medicine Constitution Assessment System Based on Multimodal Clinical Feature Representation and Fusion[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(11): 13200-13202.
[3] Chen X, Xu H, Qian P, et al. Multi-kernel Convolutional Neural Network for Wrist Pulse Signal Classification[C]//2022 32nd Conference of Open Innovations Association (FRUCT). IEEE, 2022: 75-86.
Demos
[1] Mao H, Zhang B, Xu H, et al. Robust-MSA: Understanding the impact of modality noise on multimodal sentiment analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2023, 37(13): 16458-16460.
[2] Mao H, Yuan Z, Xu H, et al. M-sena: An integrated platform for multimodal sentiment analysis[J]. arXiv preprint arXiv:2203.12441, 2022.
[3] Mao H, Zhang B, Xu H, et al. An End-to-End Traditional Chinese Medicine Constitution Assessment System Based on Multimodal Clinical Feature Representation and Fusion[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(11): 13200-13202.
[4] Wu Z, Fang J, Xu H, et al. An In-depth Interactive and Visualized Platform for Evaluating and Analyzing MRC Models[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2022: 5044-5048.
[5] Zhang H, Li X, Xu H, et al. TEXTOIR: An integrated and visualized platform for text open intent recognition[J]. arXiv preprint arXiv:2110.15063, 2021.