1.  首页 >> 资源库 >> 中文 >> 计算所人才库
许倩倩  研究员  


                                        
研究方向：

                                        
所属部门：智能信息处理重点实验室

                                        
导师类别：博导计算机应用技术

                                        
联系方式：xuqianqian@ict.ac.cn

                                        
个人网页：https://qianqianxu010.github.io/

                                    

                                

                            


                        

                    

                

            

            

                

                    

                        

                            

                                
简       历：

                                

                                    



许倩倩，中科院计算所研究员，博士生导师，国家优秀青年基金获得者。IEEE杰出会员，CCF高级会员，CSIG高级会员。研究领域为数据挖掘、机器学习和跨媒体计算，主要关注群智计算和知识图谱等，已在TPAMI、IJCV、TIP、TKDE、ICML、NIPS、CVPR、ECCV、AAAI、IJCAI、ACM Multimedia等CCF-A类期刊和会议上发表论文60余篇。先后获得：吴文俊人工智能自然科学奖一等奖、中国图象图形学学会石青云女科学家奖、吴文俊人工智能优秀青年奖、中国人工智能学会最佳青年科技成果奖、ACM中国SIGMM新星奖、中国人工智能学会优秀博士学位论文、中国计算机学会优秀博士学位论文提名、中科院百篇优秀博士学位论文、中科院青促会会员、中科院院长优秀奖、CCF-腾讯犀牛鸟科研基金、首届CAAI-华为MindSpore学术奖励基金等奖励。2015年至今指导/联合指导博士生和硕士生10余名，其中1人次获得中国电子学会优博，1人次获得微软学者奖学金，1人次入选2021年度AI华人新星榜单，1人次获得百度奖学金全球20强，1人次获得中科院院长特别奖，2人次获得中科院百篇优秀博士学位论文，1人次获得中科院朱李月华优秀博士生奖，2人次获得中科院院长优秀奖，5人次获得博士生/硕士生国家奖学金，1人次获得海英之星奖学金，3人次获得所长特别奖，2人次获得所长优秀奖。 


 


2022.09—至今 中科院计算技术研究所智能信息处理重点实验室 研究员


　　2018.03—2022.09 中科院计算技术研究所智能信息处理重点实验室 副研究员 


　　2015.10—2018.03 中科院信息工程研究所信息安全国家重点实验室 副研究员 


　　2015.07—2015.10 中科院信息工程研究所信息安全国家重点实验室 助理研究员 


　　2013.07—2015.07 北京大学国际数学中心 博士后 


　　2007.09—2013.07 中国科学院大学 计算机科学与技术学院 博士生 



                                

                            

                            

                                
主要论著：

                                

                                    
期刊文章：


[TPAMI 22] Zhiyong Yang, Qianqian Xu, Shilong Bao, Yuan He, Xiaochun Cao and Qingming Huang. Optimizing Two-way Partial AUC with an End-to-end Framework. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (Regular paper, DOI:10.1109/TPAMI. 2022.3185311)


[TPAMI 22] Ke Ma, Qianqian Xu, Jinshan Zeng, Guorong Li, Xiaochun Cao, and Qingming Huang. A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation is the Fixed Point of Adversarial Game. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (Regular paper, DOI: 10.1109/TPAMI.2022.3190939)


[TPAMI 22] Zitai Wang, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao, Qingming Huang. Optimizing Partial Area Under the Top-k Curve: Theory and Practice. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (Regular paper, DOI: 10.1109 /TPAMI.2022.3199970)


[TPAMI 22] Qianqian Xu, Zhiyong Yang, Yangbangyan Jiang, Xiaochun Cao, Yuan Yao and Qingming Huang. Not All Samples are Trustworthy: Towards Deep Robust SVP Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(6): 3154–3169, Jun. 2022. (Regular paper)


[TPAMI 22] Yangbangyan Jiang, Xiaodan Li, Yuefeng Chen, Yuan He, Qianqian Xu, Zhiyong Yang, Xiaochun Cao and Qingming Huang. MaxMatch: Semi-Supervised Learning with Worst-Case Consistency. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. (Regular paper, DOI: 10.1109/TPAMI.2022.3208419)


[TPAMI 21] Zhiyong Yang, Qianqian Xu, Xiaochun Cao and Qingming Huang. Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(11):4094–4110, Nov. 2021. (Regular paper)


[TPAMI 21] Ke Ma, Qianqian Xu, Jinshan Zeng, Xiaochun Cao and Qingming Huang. Poisoning Attack against Estimating from Pairwise Comparisons. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(10): 6393–6408, Oct. 2022. (Regular paper)


[TPAMI 21] Zhiyong Yang, Qianqian Xu, Shilong Bao, Xiaochun Cao and Qingming Huang. Learning with Multiclass AUC: Theory and Algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(11): 7747–7763, Nov. 2022. (Regular paper)


[TPAMI 21] Tianwei Cao, Qianqian Xu, Zhiyong Yang and Qingming Huang. Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 44(11): 8449–8464, Nov. 2022. (Regular paper)


[TPAMI 21] Shilong Bao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao and Qingming Huang. Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021. (Regular paper, DOI: 10.1109/TPAMI.2022.3141095)


[TPAMI 19] Qianqian Xu, Jiechao Xiong, Xiaochun Cao, Qingming Huang and Yuan Yao. From Social to Individuals: A Parsimonious Path of Multi-level Models for Crowdsourced Preference Aggregation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 41(4): 844–856, Apr. 2019. (Regular paper)


[IJCV 21] Qianqian Xu, Jiechao Xiong, Xiaochun Cao, Qingming Huang and Yuan Yao. Evaluating Visual Properties via Robust HodgeRank. International Journal of Computer Vision (IJCV), 129(5): 1732–1753, Mar. 2021. (Regular paper)


会议文章：


[ICML 22] Wenzheng Hou, Qianqian Xu, Zhiyong Yang, Shilong Bao, Yuan He and Qingming Huang. AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems. International Conference on Machine Learning (ICML), 8903–8925, 2022.


[ICML 21] Zhiyong Yang, Qianqian Xu, Shilong Bao, Yuan He, Xiaochun Cao and Qingming Huang. When All We Need is a Piece of the Pie: A Generic Framework for Optimizing Two-way Partial AUC. International Conference on Machine Learning (ICML), 11820–11829, 2021. (Long talk)


[ICML 16] Qianqian Xu, Jiechao Xiong, Xiaochun Cao and Yuan Yao. False Discovery Rate Control and Statistical Quality Assessment of Annotators in Crowdsourced Ranking. International Conference on Machine Learning (ICML), 1282–1291, 2016. (Oral)


[NeurIPS 22] Peisong Wen, Qianqian Xu, Zhiyong Yang, Yuan He and Qingming Huang. Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.


[NeurIPS 22] Zitai Wang, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao and Qingming Huang. OpenAUC: Towards AUC-Oriented Open-Set Recognition. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.


[NeurIPS 22] Shilong Bao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao and Qingming Huang. The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.


[NeurIPS 22] Zongsheng Cao, Qianqian Xu, Zhiyong Yang, Yuan He, Xiaochun Cao and Qingming Huang. OTKGE: Multi-modal Knowledge Graph Embeddings via Optimal Transport. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.


[NeurIPS 22] Huiyang Shao, Qianqian Xu, Zhiyong Yang, Shilong Bao and Qingming Huang. Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm. Annual Conference on Neural Information Processing Systems (NeurIPS), 2022.


[NeurIPS 21] Peisong Wen, Qianqian Xu, Zhiyong Yang, Yuan He and Qingming Huang. When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking. Annual Conference on Neural Information Processing Systems (NeurIPS), 5025–5037, 2021.


[NeurIPS 19] Qianqian Xu, Xinwei Sun, Zhiyong Yang, Xiaochun Cao, Qingming Huang and Yuan Yao. iSplit LBI: Individualized Partial Ranking with Ties via Split LBI. Annual Conference on Neural Information Processing Systems (NeurIPS), 3896–3906, 2019.


[NeurIPS 19] Yangbangyan Jiang, Qianqian Xu, Zhiyong Yang, Xiaochun Cao and Qingming Huang. DM2C: Deep Mixed-Modal Clustering. Annual Conference on Neural Information Processing Systems (NeurIPS), 5880–5890, 2019. (Spotlight)


[NeurIPS 19] Zhiyong Yang, Qianqian Xu, Yangbangyan Jiang, Xiaochun Cao and Qingming Huang. Generalized Block-Diagonal Structure Pursuit: Learning Soft Latent Task Assignment against Negative Transfer. Annual Conference on Neural Information Processing Systems (NeurIPS), 5846–5857, 2019.


专利：


[1] 一种视频质量评价方法，发明专利，专利号：201110195375.4.


[2] 一种视频质量客观评价方法，发明专利，专利号：201110194206.9.


[3] 一种推荐模型的训练方法、介质、电子设备和推荐模型，发明专利，专利号：202011109159.9. 


[4] 融合元路径语义的推荐方法及系统，发明专利，申请号：202110198542.4


[5] 一种用于冷启动广告点击率预估模型的元模型训练方法，发明专利，申请号：202011209043.2. 


[6] 一种知识图谱嵌入模型的训练方法、系统和电子设备，发明专利，申请号：202011040457.7. 


[7] 一种基于协同知识图谱的个性化推荐方法，发明专利，申请号：202011187518.2. 


[8] 基于多几何模型融合的结构一致性运动分割方法和系统，发明专利，申请号：202110220558.0. 


[9] 针对排序系统鲁棒性的评估方法及系统，发明专利，申请号：202110172338.5. 


[10] 基于深度PU学习与类别先验估计的数据分类方法及系统，发明专利，申请号：202111591020.7.

                                

                            

                            

                                
科研项目：

                                

                                    




1. 国家自然科学基金优秀青年科学基金，基于几何拓扑的群智计算研究，在研，项目负责人 


2. 国家自然科学基金面上基金，基于网络众包的主观视觉属性偏序算法研究，在研，项目负责人 


3. 国家自然科学基金面上基金，基于几何拓扑的网络众包策略研究，已结题，项目负责人  


4. 科技部，科技创新2030-“新一代人工智能”重大项目，跨模态医疗分析推理技术与系统，在研，子课题负责人  


5. 北京市自然科学基金面上基金，基于几何拓扑的网络众包数据分析，已结题，项目负责人 


6. CCF-腾讯犀牛鸟基金，网络众包比对数据异常值检测，已结题，项目负责人  


7. 首届CAAI-华为MindSpore学术奖励基金，面向复杂应用场景的高效、可泛化AUC优化理论及算法研究，已结题，项目负责人 


8. 国家自然科学基金青年基金，基于组合Hodge理论的图像视频质量评价方法，已结题，项目负责人 


9. 中国博士后科学基金特等资助，基于网络众包的图像视频质量评价方法研究，已结题，项目负责人  


10. 中国博士后科学基金面上资助一等，基于几何拓扑的多媒体质量主观评价方法研究，已结题，项目负责人 





                                

                            

                            

                                
获奖及荣誉：

                                

                                    



2020年 吴文俊人工智能自然科学一等奖  


2020年 CSIG石青云女科学家奖  


2018年 吴文俊人工智能优秀青年奖  


2018年 中国人工智能学会最佳青年科技成果奖  


2018年 ACM中国SIGMM新星奖  


2015年 中国人工智能学会优秀博士学位论文


2014年 中科院百篇优秀博士学位论文