2021年1月,1995年4月出生的冯磊被重庆大学计算机学院直接引进红神青年学者,聘为博士生导师、教授。主要研究方向为机器学习、数据挖掘、人工智能。聪明的。
冯磊加入公司时年仅26岁。这是各大计算机学院最年轻的引进人才,也是该校历史上首次直接为应届博士毕业生提供研究生/博士生导师。

入职半年,冯磊撰写的论文《Pointwise Binary Classification with Pairwise Confidence Comparisons》发表在第38届机器学习国际会议(CCF Class A)上。这是机器学习领域公认的顶级国际学术会议,在学术界享有盛誉。这也是重庆大学计算机学院首次作为第一单位在大会上发表学术论文,实现零突破。

冯磊简介
重庆大学洪申青年学者冯磊引进人才(教授、博士生导师),兼任日本理化研究所理化所高级智能项目(RIKEN Center for Advanced Intelligence Project)访问学者。博士毕业于新加坡南洋理工大学(Nanyang Technological University, Singapore)。早年毕业后,获得南洋理工大学计算机科学与工程学院NTU SCSE优秀博士论文二等奖。 .
中国计算机学会(CCF)会员,中国人工智能学会(CAAI)会员,国际人工智能促进会(AAAI)会员,美国计算机学会(ACM)会员,中国机器学习委员会会员人工智能协会通讯委员会成员。担任IJCAI 2021和AAAI 2022的高级程序委员会成员,ICML 2021的专家评审员,以及其他国际顶级(CCF A)会议(包括NeurIPS、KDD、CVPR、ICCV、AAAI)程序委员会成员/审稿人,并应邀担任多个国际顶级期刊(包括JMLR、IEEE-TPAMI、IEEE-TIP、IEEE-TNNLS、MLJ)的审稿人。
主要研究方向为机器学习、数据挖掘和人工智能。已参加机器学习国际会议 (ICML)、神经信息处理系统年会 (NeurIPS)、ACM SIGKDD 知识发现和数据挖掘会议 (KDD)、IEEE/CVF 计算机视觉和模式识别会议 (CVPR),国际在计算机视觉会议(ICCV)、AAAI人工智能会议(AAAI)、国际人工智能联合会议(IJCAI)、一区期刊等国际顶级(CCF A类)会议发表论文近20篇中国科学院院士。
冯磊还入选了2021福布斯中国30位30岁以下科学与医疗健康榜。

重庆大学是教育部直属的全国重点大学,是国家“211工程”和“985工程”重点建设项目一所高水平研究型综合性大学,国家“世界一流大学建设大学(A类)”。

学校始建于1929年,1940年代发展成为拥有文、理、工、商、法、医6个学院的国立综合性大学。 1952年全国院系调整后,成为高教部直属多科性大学(1958年高教部并入教育部),以工科为主。 1960年被确定为全国重点大学。改革开放以来,学校大力发展人文社会科学学科,促进多学科协调发展,逐步发展成为综合性研究型大学。 1998年学校成为国家“211工程”重点建设高校。 2000年5月,原重庆大学、重庆建筑大学、重庆建筑学院合并组建新的重庆大学。 2001年学校成为“985工程”重点建设高校。 2004年,学校被确定为中层管理大学。 2017年9月,学校入选国家“世界一流大学建设大学(A类)”。
学校学科门类齐全,涵盖理、工、经、管、法、文学、历史、哲学、医学、教育、艺术等11个学科门类。下设7个科室、35个学院,以及附属肿瘤医院、附属三峡医院、附属中心医院。在华教职工5300余人,在校学生47000余人,其中研究生20000余人,本科生26000余人,留学生1700余人。校园占地5200余亩,包括A校区、B校区、C校区和湖西校区。
冯磊学术成果
[20] Tao Liang, Guosheng Lin, Lei Feng, Yan Zhang, Fengmao Lv. Attention is not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion. Proceedings of the International Conference on Computer Vision (ICCV'21), to appear, 2021. (CCF A)[19] Lei Feng, Senlin Shu, Yuzhou Cao, Lue Tao, Hongxin Wei, Tao Xiang, Bo An, Gang Niu. Multiple-Instance Learning from Similar and Dissimilar Bags. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'21), to appear, 2021. (CCF A)[18] Lei Feng, Senlin Shu, Nan Lu, Bo Han, Xin Geng, Gang Niu, Bo An, Masashi Sugiyama. Pointwise Binary Classification with Pairwise Confidence Comparisons. Proceedings of the 38th International Conference on Machine Learning (ICML'21), to appear, 2021. (CCF A)[17] Yuzhou Cao, Lei Feng, Xitian Xu, Bo An, Gang Niu, Masashi Sugiyama. Learning from Similarity-Confidence Data. Proceedings of the 38th International Conference on Machine Learning (ICML'21), to appear, 2021. (CCF A)[16] Dengbao Wang, Lei Feng, Minling Zhang. Learning from Complementary Labels via Partial-Output Consistency Regularization. Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI'21), to appear, 2021. (CCF A)[15] Zhuoyi Lin, Lei Feng*, Rui Yin, Chi Xu, Chee Keong Kwoh. GLIMG: Global and Local Item Graphs for Top-N Recommender Systems. Information Sciences (INS), to appear, 2021. (IF=6.795, 中科院一区, *通讯作者)[14] Lei Feng, Jiaqi Lv, Bo Han, Miao Xu, Gang Niu, Xin Geng, Bo An, Masashi Sugiyama. Provably consistent Partial-Label Learning. Proceedings of the 34th Annual Conference on Neural Information Processing Systems (NeurIPS'20), to appear, 2020. (CCF A)[13] Lei Feng*†, Takuo Kaneko†, Bo Han, Gang Niu, Bo An, Masashi Sugiyama. Learning with Multiple Complementary Labels. Proceedings of the 37th International Conference on Machine Learning (ICML'20), pp.3072-3081, 2020. (CCF A, *通讯作者, †共同一作)[12] Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, Masashi Sugiyama. Progressive Identification of True Labels for Partial-Label Learning. Proceedings of the 37th International Conference on Machine Learning (ICML'20), pp.6500-6510, 2020. (CCF A)[11] Jun Huang*, Linchuan Xu, Jing Wang, Lei Feng*, Kenji Yamanishi. Discovering Latent Class Labels for Multi-Label Learning. Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI'20), pp.3058-3064, 2020. (CCF A, *通讯作者)[10] Lei Feng, Senlin Shu, Zhuoyi Lin, Fengmao Lv, Li Li, Bo An. Can Cross Entropy Loss Be Robust to Label Noise? Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI'20), pp.2206-2212, 2020. (CCF A)[9] Hongxin Wei, Lei Feng*, Xiangyu Chen, Bo An. Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20), pp.13726-13735, 2020. (CCF A, *通讯作者)[8] Lei Feng, Jun Huang, Senlin Shu, Bo An. Regularized Matrix Factorization for Multi-Label Learning with Missing Labels. IEEE Transactions on Cybernetics (IEEE-TCYB), DOI: 10.1109/TCYB.2020.3016897. (IF=11.079, 中科院一区)[7] Yan Yan, Shining Li, Lei Feng*. Partial Multi-Label Learning with Mutual Teaching. Knowledge-Based Systems (KBS), DOI: 10.1016/j.knosys.2020.106624. (IF=5.921, 中科院一区, *通讯作者)[6] Lei Feng, Hongxin Wei, Qingyu Guo, Zhuoyi Lin, Bo An. Embedding-Augmented Generalized Matrix Factorization for Recommendation with Implicit Feedback. IEEE Intelligent Systems (IEEE-IS), DOI: 10.1109/MIS.2020.3036136. (IF=3.21, 中科院三区)[5] Lei Feng, Bo An. Partial Label Learning with Self-Guided Retraining. Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), pp.3542-3549, 2019. (CCF A)[4] Lei Feng, Bo An, Shuo He. Collaboration based Multi-Label Learning. Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI'19), pp.3550-3557, 2019. (CCF A)[3] Lei Feng, Bo An. Partial Label Learning by Semantic Difference Maximization. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19), pp.2294-2300, 2019. (CCF A)[2] Shuo He, Lei Feng, Li Li. Estimating Latent Relative Labeling Importances for Multi-Label Learning. Proceedings of the 2018 IEEE Conference on Data Mining (ICDM'18), pp.1013-1018, 2018. (CCF B)[1] Lei Feng, Bo An. Leveraging Latent Label Distributions for Partial Label Learning. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI'18), pp.2107-2113, 2018. (CCF A)