马千里
博士，教授，博士生导师
电子邮箱：qianlima at scut dot edu dot cn
主页：http://www2.scut.edu.cn/qianlima
办公电话： (+86)20-39380297转3513 办公室：B7-51
邮寄地址：广州大学城华南理工大学计算机科学与工程学院 510006
（本人2025级硕士生和博士生的名额已满）
个人简介
马千里，博士，教授，博士生导师。2008年6月于华南理工大学获得工学博士学位，同年7月留校任教。2016年3月至2017年3月，为美国加州大学（圣地亚哥分校）访问学者。主要从事人工智能、机器学习和数据挖掘等相关领域的研究工作，已发表文章100余篇，其中多项成果发表在NeurIPS、AAAI、IJCAI、ACL、EMNLP、KDD、ICDE、CIKM、IEEE TPAMI、IEEE TNNLS、IEEE TCYB、IEEE TASLP、Neural Networks、Information Sciences等国际顶级会议及期刊上。主持国家及省部级项目20余项，参与国家及省部级项目10余项，包括国家重点研发计划项目2项，国家自然科学基金重点项目1项，曾获得广东省科技进步奖二等奖，中国南方电网广东电网公司科技进步二等奖，广东省计算机学会优秀论文一等奖，华南理工大学教学优秀奖一等奖。目前担任国际期刊TASLP的副主编、中国人工智能学会机器学习专委会委员，中国人工智能学会知识工程与分布式智能专委会委员，中国计算机学会人工智能与模式识别专委会委员，广东省计算机学会计算智能专委会副主任，以及IEEE TPAMI、IEEE TNNLS、IEEE TSMC、IEEE TCYB、《中国科学》、《软件学报》、《自动化学报》、NeurIPS、ICML、ICLR、AAAI、IJCAI、KDD、ACL、EMNLP等多个知名期刊和会议审稿人或（高级）程序委员会委员等学术兼职。
研究兴趣
以人工智能、机器学习和数据挖掘为主要研究方向，以建立面向时间序列数据学习、自然语言处理的新型机器学习算法、深度学习模型为主要目标，推动将研究成果应用于教育、电力、传统制造、金融等领域。
学术/社会兼职：
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)副主编
中国计算机学会（CCF）高级会员，IEEE 会员
中国人工智能学会机器学习专业委员会委员
中国人工智能学会知识工程与分布式智能专业委员会委员
中国计算机学会人工智能与模式识别专业委员会委员
研究成果
代表论文:
Times Series:
*: 通讯作者
31. Zhen Liu, Peitian Ma, Dongliang Chen, Wenbin Pei, Qianli Ma*. Scale-teaching: Robust Multi-scale Training for Times Series Classification with Noisy Labels[C]//Advances in neural information processing systems (NeurlPS), 2023. [paper][code]
30. Siying Zhu, Jiawei Zheng, Qianli Ma*. MR-Transformer: Multiresolution Transformer for Multivariate Time Series Prediction[J]. IEEE Transactions on Neural Networks and Learning Systems(TNNLS), 2023. [paper]
29. Peitian Ma, Zhen Liu, Junhao Zheng, Linhao Wang, Qianli Ma*. CTW: Confident Time-Warping for Time-Series Label-Noise Learning[C]//IJCAI. 2023: 4046-4054.[paper][code]
28. Zhen Liu, Chuxin Chen, Qianli Ma. Category-aware optimal transport for incomplete data classification[J]. Information Sciences, 2023, 634: 443-476. [paper]
27. Zhen Liu, Qianli Ma*, Peitian Ma, Linghao Wang. Temporal-Frequency Co-training for Time Series Semi-supervised Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence(AAAI), 2023, 37(7): 8923-8931. [paper][code]
26. Huizi Lyu, Desen Huang, Sen Li, Wing W.Y.Ng, Qianli Ma. Multiscale echo self-attention memory network for multivariate time series classification[J]. Neurocomputing, 2023, 520: 60-72. [paper]
25. Desen Huang, Lifeng Shen, Zhongzhong Yu, Zhenjing Zheng, Min Huang, Qianli Ma*. Efficient time series anomaly detection by multiresolution self-supervised discriminative network[J]. Neurocomputing, 2022, 491: 261-272. [paper]
24. Qianli Ma*, Zipeng Chen, Shuai Tian, Wing W.Y.Ng. Difference-guided representation learning network for multivariate time-series classification[J]. IEEE Transactions on Cybernetics, 2020, 52(6): 4717-4727. [paper]
23. Qianli Ma*, Sen Li, Garrison W.Cottrell. Adversarial joint-learning recurrent neural network for incomplete time series classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 44(4): 1765-1776. [paper]
22. Zipeng Chen, Qianli Ma*, Zhenxi Lin. Time-Aware Multi-Scale RNNs for Time Series Modeling[C]//IJCAI. 2021: 2285-2291. [paper]
21. Qianli Ma*, Zhenjing Zheng, Jiawei Zheng, Sen Li, Wangqing Zhuang, Garrison W. Cottrell. Joint-Label Learning by Dual Augmentation for Time Series Classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence(AAAI). 2021, 35(10): 8847-8855. [paper]
20. Lifeng Shen, Zhongzhong Yu, Qianli Ma*, James T. Kwok. Time series anomaly detection with multiresolution ensemble decoding[C]//Proceedings of the AAAI Conference on Artificial Intelligence(AAAI). 2021, 35(11): 9567-9575. [paper]
19. Qianli Ma*, Zhenjing Zheng, Wanqing Zhuang, Enhuan Chen, Jia Wei, Jiabing Wang. Echo memory-augmented network for time series classification[J]. Neural Networks, 2021, 133: 177-192. [paper]
18. Qianli Ma*, Sen Li, Garrison W. Cottrell. Adversarial joint-learning recurrent neural network for incomplete time series classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(TPAMI), 2020, 44(4): 1765-1776. [paper]
17. Qianli Ma*, Zipeng Chen, Shuai Tian, Wing W. Y. Ng. Difference-guided representation learning network for multivariate time-series classification[J]. IEEE Transactions on Cybernetics, 2020, 52(6): 4717-4727. [paper]
16. Qianli Ma*, Sen Li, Wanqing Zhuang, Sen Li, Jiabing Wang, Delu Zeng. Self-supervised time series clustering with model-based dynamics[J]. IEEE Transactions on Neural Networks and Learning Systems(TNNLS), 2020, 32(9): 3942-3955. [paper]
15. Qianli Ma*, Zhenxi Lin, Enhuan Chen, Garrison W. Cottrell. Temporal pyramid recurrent neural network[C]//Proceedings of the AAAI Conference on Artificial Intelligence(AAAI). 2020, 34(04): 5061-5068. [paper]
14. Qianli Ma*, Wanqing Zhuang, Sen Li, Desen Huang, Garrison. Adversarial dynamic shapelet networks[C]//Proceedings of the AAAI conference on artificial intelligence(AAAI). 2020, 34(04): 5069-5076. [paper]
13. Qianli Ma*, Jiawei Zheng, Sen Li, Garrison W. Cottrell. Learning representations for time series clustering[J]. Advances in neural information processing systems(NeurlPS), 2019, 32. [paper]
12. Qianli Ma*, Wangqing Zhuang, Garrison W. Cottrell. Triple-shapelet networks for time series classification[C]//2019 IEEE International Conference on Data Mining (ICDM). IEEE, 2019: 1246-1251. [paper]
11. Qianli Ma*, Lifeng Shen, Garrison W. Cottrell. DeePr-ESN: A deep projection-encoding echo-state network[J]. Information Sciences, 2020, 511: 152-171. [paper]
10. Qianli Ma*, Shuai Tian, Jia Wei, Wing W. Y. Ng. Attention-based spatio-temporal dependence learning network[J]. Information Sciences, 2019, 503: 92-108.[paper]
9. Qianli Ma*, Enhuan Chen, Zhenxi Lin, Jiangyue Yan, Zhiwen Yu, Wing W. Y. Ng. Convolutional multitimescale echo state network[J]. IEEE Transactions on Cybernetics, 2019, 51(3): 1613-1625.[paper]
8. Qianli Ma*, Wangqing Zhuang, Lifeng Shen, Garrison W. Cottrell. Time series classification with echo memory networks[J]. Neural networks, 2019, 117: 225-239.[paper]
7. Qianli Ma*, Sen Li, Lifeng Shen, Jiabing Wang, Jia wei, Zhiwen Yu, Garrison W. Cottrell. End-to-end incomplete time-series modeling from linear memory of latent variables[J]. IEEE transactions on cybernetics, 2019, 50(12): 4908-4920.[paper]
6. Kejian Shi, Hongyang Qin, Chijun Sima, Sen Li, Lifeng Shen, Qianli Ma*. Dynamic barycenter averaging kernel in RBF networks for time series classification[J]. IEEE Access, 2019, 7: 47564-47576.[paper]
5. Lifeng Shen, Qianli Ma*, Sen Li. End-to-end time series imputation via residual short paths[C]//Asian conference on machine learning(ACML), 2018: 248-263.[paper]
4. Qianli Ma*, Lifeng Shen, Enhuan Chen, Shuai Tian, Jiabing Wang, Garrison W. Cottrell. WALKING WALKing walking: Action Recognition from Action Echoes[C]//IJCAI. 2017: 2457-2463.[paper]
3. Qianli Ma*, Lifeng Shen, Garrison W. Cottrell. Deep-esn: A multiple projection-encoding hierarchical reservoir computing framework[J]. arXiv preprint arXiv:1711.05255, 2017.[paper]
2. Qianli Ma*, Lifeng Shen, Wanqing Zhuang, Jieyu Chen. Decouple Adversarial Capacities with Dual-Reservoir Network[C]//Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14–18, 2017, Proceedings, Part V 24. Springer International Publishing, 2017: 475-483.[paper]
1. Qianli Ma*, Lifeng Shen, Ruishi Su, Jieyu Chen. Two-stage temporal multimodal learning for speaker and speech recognition[C]//Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part II 24. Springer International Publishing, 2017: 64-72.[paper]
Natural Language Processing(NLP):
*: 通讯作者
16. Jinsong Yan, Piji Li, Haibin Chen, Junhao Zheng, Qianli Ma*. Does the Order Matter? A Random Generative Way to Learn Label Hierarchy for Hierarchical Text Classification[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2023. [paper]
15. Huawen Feng, Zhenxi Lin, Qianli Ma*. Perturbation-Based Self-Supervised Attention for Attention Bias in Text Classification[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2023, 31: 3139-3151. [paper]
14. Huawen Feng, Junlong Liu, Junhao Zheng, Haibin Chen, Xichen Shang, Qianli Ma*. Joint Constrained Learning with Boundary-adjusting for Emotion-Cause Pair Extraction[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics(ACL), 2023: 1118-1131. [paper]
13. Junhao Zheng, Qianli Ma*, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen. Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics(ACL), 2023: 9155-9173 [paper]
12. Xichen Shang, Chuxin Chen, Zipeng Chen, Qianli Ma*. Modularized Mutuality Network for Emotion-Cause Pair Extraction[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2022, 31: 539-549. [paper]
11. Junhao Zheng, Haibin Chen, Qianli Ma*. Cross-domain Named Entity Recognition via Graph Matching[C]//Findings of the Association for Computational Linguistics(ACL), 2022. 2022: 2670-2680. [paper]
10. Junlong Liu, Xichen Shang, Qianli Ma*. Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction[C]//Conference on Empirical Methods in Natural Language Processing(EMNLP), 2022:5339-5351. [paper]
9. Junhao Zheng, Zhanxian Liang, Haibin Chen, Qianli Ma*. Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition[C]//Conference on Empirical Methods in Natural Language Processing(EMNLP), 2022:3602-3615. [paper][code]
8. Huawen Feng, Qianli Ma*. It’s Better to Teach Fishing than Giving a Fish: An Auto-Augmented Structure-aware Generative Model for Metaphor Detection[C]//Findings of Conference on Empirical Methods in Natural Language Processing(EMNLP), 2022: 656-667. [paper]
7. Haibin Chen, Qianli Ma*, Zhenxi Lin, Jiangyue Yan. Hierarchy-aware label semantics matching network for hierarchical text classification[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(ACL) (Volume 1: Long Papers). 2021: 4370-4379. [paper]
6. Xichen Shang, Qianli Ma*, Zhenxi Lin, Jiangyue Yan, Zipeng Chen. A Span-based Dynamic Local Attention Model for Sequential Sentence Classification[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(ACL) (Volume 2: Short Papers). 2021: 198-203. [paper]
5. Haibin Chen, Qianli Ma*, Liuhong Yu, Zhenxi Lin, Jiangyue Yan. Corpus-Aware Graph Aggregation Network for Sequence Labeling[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2021, 29: 2048-2057. [paper]
4. Qianli Ma*, Jiangyue Yan, Zhenxi Lin, Liuhong Yu, Zipeng Chen. Deformable Self-Attention for Text Classification[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2021, 29: 1570-1581. [paper]
3. Qianli Ma*, Zhenxi Lin, Jiangyue Yan, Zipeng Chen, Liuhong Yu. Mode-LSTM: a parameter-efficient recurrent network with multi-scale for sentence classification[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020: 6705-6715. [paper]
2. Qianli Ma*, Liuhong Yu, Shuai Tian, Enhuan Chen, Wing W. Y. Ng. Global-local mutual attention model for text classification[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2019, 27(12): 2127-2139. [paper]
1. Luoqin Li, Jiabing Wang, Jichang Li, Qianli Ma*, Jia Wei. Relation classification via keyword-attentive sentence mechanism and synthetic stimulation loss[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing(TASLP), 2019, 27(9): 1392-1404. [paper]
Others:
4. Sen Li, Fuyu Lv, Taiwei Jin, Yukun Zheng, Tao Zhuang, Qingwen Liu, Xiaoyi Zeng, James T.Kwok, Qianli Ma*. Query Rewriting in TaoBao Search[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management(CIKM). 2022: 3262-3271. [paper]
3. Jiawei Zheng, Qianli Ma*, Hao Gu, Zhenjing Zheng. Multi-view denoising graph auto-encoders on heterogeneous information networks for cold-start recommendation[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining(KDD). 2021: 2338-2348. [paper]
2. Sen Li, Fuyu Lv, Taiwei Jin, Guli Lin, Keping Yang, Xiaoyi Zeng, Xiaoming Wu, Qianli Ma*. Embedding-based product retrieval in taobao search[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining(KDD). 2021: 3181-3189. [paper]
1. Wenguang Yuan, Jia Wei, Jiabing Wang, Qianli Ma, Tolga Tasdizen. Unified attentional generative adversarial network for brain tumor segmentation from multimodal unpaired images[C]//Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part III 22. Springer International Publishing, 2019: 229-237. [paper]
部分项目：
1. 广东省科技计划项目(国际科技合作领域). “面向大规模时间序列数据表示学习的研究”，编号：2023A0505050106，项目起止时间：2023年9月-2025年9月.
2. 南方电网科研院项目，“配电网智能交互框架及边缘计算资源分配关键技术研究”，编号：2023440002001056，项目起止时间：2023年4月-2024年9月.
3. 国家自然科学基金面上项目,“面向低质量时间序列的鲁棒性表示学习”, 编号：62272173，项目起止时间：2023
年1月-2026年12月.
4. 广东省自然科学基金面上项目，“面向现实复杂场景中的时间序列数据建模”，编号：2022A1515010179，项
目起止时间：2022年1月-2024年12月.
5. 国家自然科学基金项目，“基于高维随机投影的深度储备池计算模型研究”，编号：61872148，项目起止时间：2019年1月-2022年12月。
6. 国家自然科学基金项目，“多尺度模块网络下的储备池神经计算模型及算法研究”，编号：61502174，项目起止时间：2016年1月-2018年12月。
7. 广州市科技计划项目-产学研协同创新重大专项，“基于深度学习的商业智能分析平台关键技术研发”，编号：201704030051，项目起止时间：2017年5月-2019年12月。
------------------------------------------------------------------------------------------
实验室成员
在读学生
博士生
2023 吴斌权
2022 郑俊豪 邝涛杰 冯华文
2021 柳真
硕士生
2023 邱圣洁 吴钺 罗奕城 陈家豪
2022 刘俊龙 张崇志 严景松 汪灵浩
2021 袁海桃 刘嘉麒 程雨
已毕业学生
2020 陈海斌（@阿里） 陈楚鑫（@阿里） 朱思颖（@腾讯） 尚曦辰（@字节）
2019 郑佳炜（@腾讯） 郑镇境（@腾讯） 陈子鹏（@蚂蚁） 余忠忠（@字节）
2018 黄德森（@百度） 李森（@字节） 林镇溪（@腾讯） 闫江月（@京东）
2017 余柳红（@华为） 庄万青（@腾讯） 李森（@阿里）
2016 陈恩欢（@YY语音） 田帅（@微信）
2015 沈礼锋（@香港科大）
2012 蒋佳军（@百度)
2010 陈威彪（@民航局）
2009 林泽鑫（联合指导，@易方达基金) 周卫敏（联合指导，@中兴）
2008 吴广财（联合指导，@广东电网） 郑杰生（联合指导，@广东电网）
------------------------------------------------------------------------------------------
教授课程：离散数学、深度学习
招生要求(本科生SRP、实习、研究生等）:
1.对人工智能领域感兴趣；成绩好；逻辑思维清晰；算法编程能力强；能不太困难的阅读英文文献；能吃苦
2.修读或自学过以下课程：
线性代数 概率统计 算法分析与设计 机器学习
3.掌握至少一门工具：C++、JAVA、Python、Matlab
4.参加过ACM竞赛、数模竞赛等（此项非必备条件）
5.需要本人写推荐信的同学请注意，为了使推荐信评价更客观公正，本人只给在我们组至少工作过6个月（含）以上的同学写推荐信，请谅解。
