苏勤亮

副教授

联系邮箱： suqliang@mail.sysu.edu.cn

联系地址： 广州大学城外环东路132号jbo竞博电竞官方网站超算中心503M

教师简介: 

苏勤亮，jbo竞博电竞官方网站副教授、博士生导师，主要研究兴趣包括机器学习模型和算法研究及应用、概率统计学习、自然语言处理。他于2014年从香港大学获得博士学位，之后前往美国杜克大学电子与计算机工程系从事博士后研究工作，2018年1月回国加入jbo竞博电竞官方网站至今。作为项目负责人，近年来承担了包括国家自然科学基金青年项目、面上项目、科技委项目、广东省自然科学基金等多项国家及省部级研究项目，以及多项企业委托合作项目。在包括中国计算机学会CCF推荐的A/B类会议和中国科学院推荐的重要期刊（如：ICML, NIPS, AAAI, IJCAI, ACL, EMNLP，ACM MM, WWW, IEEE TKDE, IEEE TSP等）上发表论文60余篇，曾获CCF A类国际学术会议国际计算语言学大会ACL 2018最佳论文提名、2020年广东省计算机学会优秀论文一等奖。他长期担任机器学习和人工智能领域多个重要国际学术会议的领域主席（Area Chair)或（高级）程序委员会委员，如：ICML, NIPS, AAAI, IJCAI, ACL, ICLR等。

课题组在机器学习的模型算法研究及应用、概率统计学习、自然语言处理等方向都有较好的研究基础，欢迎对下面研究方向感兴趣的优秀学子与我联系，也欢迎具有较好数学基础或统计背景的学生与我联系：

1）机器学习模型和算法研究（深度生成模型、无/弱监督学习、信息论启发的学习等）；

2)  机器学习在图像、文本和图等数据上的应用（信息检索、异常检测、表征学习、关联/图数据分析）；

3)  自然语言处理；

4）统计学习，如：差分推理、MCMC采样、模型不确定性估计、贝叶斯方法等。

课题组现有3名博士生及10余名硕士生在读，已毕业1名博士及10余名硕士，毕业学生大多都前往各大厂工作或国/境外著名高校深造

2024.5.27 课题组计划招收1名2025年9月入学的博士生，欢迎对上述研究方向感兴趣的有意愿攻读博士学位（直博或申请-考核制皆可）的学生与我联系。

课题组长期招聘博士后、（副）研究员，欢迎对上述研究方向感兴趣、且有一定研究基础的已毕业或将要毕业博士来信咨询，待遇从优！

研究领域: 

机器学习、自然语言处理、统计学习

教育背景: 

  • 2010.9 — 2014.12       香港大学               博士
  • 2007.9 — 2010.3         浙江大学              硕士
  • 2003.9 — 2007.6         重庆大学             本科

工作经历: 

  • 2018.1 — 至今           jbo竞博电竞官方网站              副教授
  • 2015.3 — 2017.12       杜克大学            博士后
  • 2015.1 — 2015.2         香港大学             高级研究助理

获奖及荣誉: 

  • 国际计算语言大会ACL 2018最佳长论文提名
  • 广东省计算机学会优秀论文一等奖

主要学术兼职: 

审稿人：JMLR, IEEE TIT, IEEE TKDE, IEEE TSP, ICML, NIPS AAAI, ACL, EMNLP, ICLR, UAI, AISTATS

代表性论著: 

(* denotes equal contribution)​​

  • Wenxi Lv, Qinliang Su, Wenchao Xu, "One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning", The Thirteenth International Conference on Learning Representations (ICLR-2025), Singapore, Apr.  24-Apr. 28, 2025. (机器学习顶会)
  • Qingqing Fang, Qinliang Su, Wenxi Lv, Wenchao Xu, Jianxing Yu, “Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning”, The 39th AAAI Conference on Artificial Intelligence (AAAI-2025), Philadelphia, Pennsylvania, USA, Feb. 27-Mar. 4, 2025. (CCF A 类会议)
  • Junxi Xiao, Qinliang Su, Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing, the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS-2024), Vancouver, Canada, Dec. 9 - Dec. 15, 2024. (CCF A 类论文）
  • Zetong Li, Qinliang Su, Shijing Si, Jianxing Yu, Leveraging BERT and TFIDF Features for Short Text Clustering via Alignment-Promoting Co-Training, The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP-2024), Miami, Florida, U.S., Nov. 12 - Nov. 16, 2024. (CCF B 类论文）
  • Qian Zhang, Qinliang Su, Jiayang Chen, Zhenpeng Song, Document Hashing with Multi-Grained Prototype-Induced Hierarchical Generative Model, Findings of the 2024 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP-2024), Miami, Florida, U.S., Nov. 12 - Nov. 16, 2024. (CCF B 类论文）
  • Wenxi Lv, Qinliang Su, Hai Wan, Hongteng Xu, Wenchao Xu, Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous Data, The Forty-first International Conference on Machine Learning (ICML-2024), Vienna, Austria, Jul. 21 - Jul. 27, 2024. (CCF A类会议)
  • Qinliang Su, Bowen Tian, Hai Wan, Jian Yin, Anomaly Detection under Contaminated Data with Contamination-Immune Bidirectional GANs'', IEEE Transactions on Knowledge and Data Engineering, 2024. (CCF A类期刊， IF=8.9)
  • Yufeng Zhang, Jianxing Yu, Yanghui Rao, Libin Zheng, Qinliang Su, Huajie Zhu, Jian Yin, Domain Adaptation for Subjective Induction Questions Answering on Products by Adversarial Disentangled Learning, The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), Bangkok, Thailand, Aug. 11 - Aug. 16, 2024. (CCF A类会议)
  • Jiayang Chen, Qinliang Su, Zetong Li, Hai Wan, Document Hashing by Exploiting NoisyNeighborhood Information with Fault-TolerantMutual-Information-Preserving VAE, the 29th International Conference on Database Systems for Advanced Applications (DASFAA-2024), Gifu, Japan, Jul. 2 - Jul. 5, 2024. (CCF B类会议)
  • Zhenpeng Song, Qinliang Su, Jiayang Chen, Unsupervised Hashing with Contrastive Learning by Exploiting Similarity Knowledge and Hidden Structure of Data, Proceedings of the 31st ACM International Conference on Multimedia (ACM MM-2023), Ottawa, Canada, Oct. 29 - Nov. 3, 2023. (CCF A类会议) ​
  • Zhaoyang Wang, Zhiyue Liu, Xiaopeng Zheng, Qinliang Su, Jiahai Wang, RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks'', Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL-2023), Toronto, Canada, Jul. 9-14, 2023. (CCF A类会议)
  • Jianxing Yu, Shiqi Wang, Libin Zheng, Qinliang Su, Wei Liu, Baoquan Zhao, Jian Yin, Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial Inference, Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, Jul. 9-14, 2023. (CCF A类会议)
  • Zenan Xu, Xiaojun Meng, Yasheng Wang, Qinliang Su, Zexuan Qiu, Xin Jiang, Qun Liu, Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video, The 32nd International Joint Conference on Artificial Intelligence (IJCAI-2023)}, Macao S.A.R., China, Aug. 19-25, 2023. (CCF A类会议)
  • Zenan Xu, Wanjun Zhong, Qinliang Su, Fuwei Zhang, Cross-Modal-Aware Representation Learning with Syntactic Hypergraph Convolutional Network for VideoQA, IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia, Jul. 10-14, 2023. (CCF B类会议)
  • Zenan Xu, Qinliang Su, Junxi Xiao, Multimodal Aspect-Based Sentiment Classification with Knowledge-Injected Transformer, IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia, Jul. 10-14, 2023. (CCF B类会议)
  • Zenan Xu, Zexuan Qiu, Qinliang Su, Learning Semantic-Rich Relation-Selective Entity Representation for Knowledge Graph Completion, The 28th International Conference on Database Systems for Advanced Applications (DASFAA-2023), Tianjin, China, April. 17-20, 2023. (CCF B类会议)
  • Bowen Tian, Qinliang Su, Jianxing Yu, Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks, The 37th AAAI Conference on Artificial Intelligence (AAAI-2023), Washington, DC, USA, Feb. 7-14, 2023. (CCF A类会议)
  • Zenan Xu, Linjun Shou, Jian Pei, Ming Gong, Qinliang Su, Xiaojun Quan, Daxin Jiang, A Graph Fusion Approach for Cross-Lingual Machine Reading Comprehension, The 37th AAAI Conference on Artificial Intelligence (AAAI-2023), Washington, DC, USA, Feb. 7-14, 2023. (CCF A类会议)
  • Bowen Tian, Qinliang Su, Jian Yin, Anomaly Detection by Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANs, The 31st International Joint Conference on Artificial Intelligence (IJCAI-2022), Vienna, Austria, July 23-29, 2022. (CCF A类会议)
  • Zijing Ou, Tingyang Xu, Qinliang Su, Yingzhen Li, Peilin Zhao, Yatao Bian, ``Learning Neural Set Functions under the Optimal Subset Oracle'', The Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS-2022), New Orleans, US, Nov. 28-Dec. 9, 2022. (CCF A类会议)
  • Zexuna Qiu, Qinliang Su, Jianxing Yu, Shijing Si, ``Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization'', The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP-2022), Abu Dhabi, Dec. 7-11, 2022. (CCF B类会议)
  • Yingpeng Wen, Qinliang Su, Minghua Shen, Nong Xiao, Improving the Exploration Efficiency of DQNs via the Confidence Bound Methods, Applied Intelligence, Mar. 2022. (中科院二区， IF=5.09)
  • Zijing Ou, Qinliang Su, Jianxing Yu, Ruihui Zhao, Yefeng Zheng and Bang Liu, Refining BERT Embeddings for Document Hashing via Mutual Information Maximization, Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP-2021), Online and Punta Cana, Dominican Republic, Nov. 7-11, 2021. (CCF B类会议)
  • Feifan Yang, Tao Yang, Xiaojun Quan and Qinliang Su, Learning to Answer Psychological Questionnaire for Personality Detection, Findings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP-2021), Online and Punta Cana, Dominican Republic, Nov. 7-11, 2021. (CCF B类会议)
  • Zijing Ou, Qinliang Su, Jianxing Yu, Bang Liu, Jingwen Wang, Ruihui Zhao, Changyou Chen and Yefeng Zheng, Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval'', the 59th Annual Meeting of the Association for Computational Linguistics (ACL-21), Online, Aug. 2021. (CCF A类会议)
  • Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Daxin Jiang and Nan Duan, Syntax-Enhanced Pre-trained Model, the 59th Annual Meeting of the Association for Computational Linguistics (ACL-21), Online, Aug. 2021. (CCF A类会议)
  • Zexuan Qiu, Qinliang Su, Zijing Ou, Jianxing Yu, Changyou Chen, Unsupervised Hashing with Contrastive Information Bottleneck, The 30th International Joint Conference on Artificial Intelligence (IJCAI-21), Montreal (Online), Aug. 2021. (CCF A类会议)
  • Jianxing Yu, Qinliang Su, Xiaojun Quan, Jian Yin, Multi-hop Reasoning Question Generation and Its Application, IEEE Transactions on Knowledge and Data Engineering, 2021. (CCF A类期刊， IF=4.94)
  • Zenan Xu, Zijing Ou, Qinliang Su, Jianxing Yu, Xiaojun Quan and Zhenkun Lin, Embedding Dynamic Attributed Networks By Modeling the Evolution Processes, The 28th International Conference on Computational Linguistics (COLING-2020), Dec. 2020. (CCF B 类会议)
  • Yunyi Yang, Kun Li, Xiaojun Quan, Weizhou Shen and Qinliang Su, Constituency Lattice Encoding for Aspect Term Extraction, The 28th International Conference on Computational Linguistics (COLING-2020), Dec. 2020. (CCF B 类会议)
  • Lin Zheng, Qinliang Su, Dinghan Shen and Changyou Chen, Generative Semantic Hashing Enhanced via Boltzmann Machines, The 58th Annual Meeting of the Association for Computational Linguistics (ACL-2020), Seattle, Jul. 2020. (CCF A 类会议)
  • Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin, Low-Resource Generation of Multi-hop Reasoning Questions, The 58th Annual Meeting of the Association for Computational Linguistics (ACL-2020), Seattle, Jul. 2020. (CCF A 类会议)
  • Jianxing Yu, Xiaojun Quan, Qinliang Su and Jian Yin, Generating Multi-hop Reasoning Questions to Improve Machine Reading Comprehension, The World Wide Web Conference (WWW-2020), Taipei, April 2020. (CCF A 类会议)
  • Bing Li, Qinliang Su, Yik-Chung Wu, Fixed Points of Gaussian Belief Propagation and Relation to Convergence, IEEE Trans. Signal Process. vol. 67, no. 23, pp.6025-6038, Dec. 2019. (中科院Top期刊)
  • Wei Dong, Qinliang Su, Dinghan Shen, Changyou Chen, Document Hashing with Mixture-Prior Generative Models, 2019 Conference on Emperical Methods in Natural Language Process, EMNLP 2019, Hong Kong, 2019.11.3-11.7. (CCF B类）
  • Zenan Xu, Qinliang Su, Xiaojuan Quan, Weijia Zhang, A Deep Neural Information Fusion Architecture for Textural Network Embeddings, 2019 Conference on Emperical Methods in Natural Language Process, EMNLP 2019, Hong Kong, 2019.11.3-11.7. (CCF B类）
  • Changyou Chen, Wenlin Wang, Yizhe Zhang, Qinliang Su, Lawrence Carin, A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC," Science China: Information Science, vol. 62, Jan. 2019. （CCF B类期刊）
  • Dinghan Shen*, Qinliang Su*, Paidamoyo Chapfuwa, Wenlin Wang, GuoyinWang, Lawrence Carin, Ricardo Henao, NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing, The 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 2018.7.15-7.20. (CCF A类, Best Paper Honorable Mention)
  • Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao, Lawrence Carin, Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 2018.7.15-7.20. (CCF A类)
  • Liqun Chen, Shuyang Dai, Yunchen Pu, Chunyuan Li, Qinliang Su, Erjin Zhou, Lawrence Carin, Symmetric Variational Auto-encoder and Connections to Adversarial Learning, 21th Inter. Conf. Artificial Intelligence and Statistics, AISTATS 2018, Canary Islands, Spain, 2018.4.9-4.11. (统计人工智能著名会议)
  • Dinghan Shen, Yizhe Zhang, Ricardo Henao, Qinliang Su, Lawrence Carin, Deconvolutional Latent-Variable Model for Text Sequence Matching, 32th Proc. American Association of Artificial Intelligence, AAAI 2018, New Orleans, USA, 2018.2.2-2.7. (CCF A类)
  • Zhe Gan, Chunyuan Li, Changyou Chen, Yunchen Pu, Qinliang Su, Lawrence Carin, Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, CA, 2017.7.30-8.4. (CCF A类)
  • Qinliang Su, Xuejun Liao, Lawrence Carin, A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks, 31th Annual Conference on Neural Information Processing Systems, NIPS 2017, Long Beach, USA, 2017.12.4-12.9. (CCF A类)
  • Qinliang Su, Xuejun Liao, Chunyuan Li, Zhe Gan, Lawrence Carin, Unsupervised Learning with Truncated Gaussian Graphical Models, 31th Proc. American Association of Artificial Intelligence, AAAI 2017, San Francisco, USA, 2017.2.4-2.9. (CCF A类)
  • Qinliang Su, Xuejun Liao, Changyou Chen, Lawrence Carin, Nonlinear Statistical Learning with Truncated Gaussian Graphical Model, 33th International Conference on Machine Learning, ICML 2016, New York, USA, 2016.6.24-6.26. (CCF A类)
  • Qinliang Su, Yik-Chung Wu, Distributed estimation of variance in Gaussian graphical model via belief propagation: accuracy analysis and improvement, IEEE Trans. Signal Process., 2015, 63(23): 6258-6271. (中科院Top期刊)
  • Qinliang Su, Yik-Chung Wu, On convergence of Gaussian belief propagation, IEEE Trans. Signal Process., 2015, 63(5): 1144-1155. (中科院Top期刊)
  • Qinliang Su, Yik-Chung Wu, Convergence analysis of the variance in Gaussian belief propagation, IEEE Trans. Signal Process., 2014, 62(19): 5119-5131. (中科院Top期刊)
  • Qinliang Su, Yik-chung Wu, Determine the Convergence of Variance in Gaussian Belief Propagation via Semi-definite Programming, International Symposium on Information Theory, ISIT 2014, Honolulu, USA, 2014.6.29-2014.7.4. （信息论旗舰会议）
  • Qinliang Su, Aiping Huang, Jing Li and Hsiao-Hwa Chen, Complexity reduction of signal detection by exploiting correlation characteristics of spreading sequences, Int. J. Communication Systems, 2009, 22(11): 1427-1443. (SCI期刊)