photo

Gengyu Lyu 吕庚育

I am currently an Associate Professor (and a Ph.D. Supervisor) in the Faculty of Information Technology, Beijing University of Technology (BJUT), China. Before joining BJUT, I received my Ph.D. degree in the School of Computer and Information Technology, Beijing Jiaotong University (BJTU) in 2022, where I was fortunate to be supervised by Prof. Songhe Feng.

Research Interests

My main research interests include Machine Learning and Data Mining, especially in learning from weakly supervised multi-label data.

I am looking for highly motivated PhD and Master students with strong mathematical or programming background. Please send your CV to my email. [中文招生主页] [中文校园主页][实验室主页]

  lyugengyu AT gmail DOT com and Google Scholar Citations Page                            

News

  • 2022.07 I joined the DMS Lab in BJUT.

Selected Publications

2024

SURER: Structure-Adaptive Unified Graph Neural Network for Multi-view Clustering
Jing Wang, Songhe Feng, Gengyu Lyu, JiaZheng Yuan
AAAI Conference on Artificial Intelligence (AAAI), 2024.

A Separation and Alignment Framework for Black-box Domain Adaptation
Mingxuan Xia, Junbo Zhao, Gengyu Lyu, Zenan Huang, Tianlei Hu, Gang Chen, Haobo Wang
AAAI Conference on Artificial Intelligence (AAAI), 2024.

2023

Prior Knowledge Regularized Self-Representation Model for Partial Multi-Label Learning
Gengyu Lyu, Songhe Feng, Yi Jin, Tao Wang, Congyan Lang, Yidong Li
IEEE Transactions on Cybernetics (TCYB), 53(3):1618-1628, 2023. [PDF]

Redundant Label Learning via Subspace Representation and Global Disambiguation
Gengyu Lyu, Songhe Feng, Wei Liu, Shuoyan Liu, Congyan Lang
ACM Transactions on Intelligent Systems and Technology (ACM TIST), 14(1):15, 2023. [PDF]

Prior Knowledge Constrained Adaptive Graph Framework for Partial Label Learning
Gengyu Lyu, Songhe Feng, Shaokai Wang, Zhen Yang
ACM Transactions on Intelligent Systems and Technology (ACM TIST), 14(2):25, 2023. [PDF]

Deep Partial Multi-Label Learning with Graph Disambiguation
Haobo Wang, Shisong Yang, Gengyu Lyu (Corresponding Author), WeiWei Liu, Tianlei Hu, Ke Chen, Songhe Feng, Gang Chen
International Joint Conference on Artificial Intelligence (IJCAI), 2023 [PDF] [Codes]

Triple-Granularity Contrastive Learning for Deep Multi-View Subspace Clustering
Jing Wang, Songhe Feng, Gengyu Lyu, Zhibin Gu
ACM International Conference on Multimedia (ACM MM), 2023.

MetaZSCIL: A Meta-Learning Approach for Generalized Zero-Shot Class Incremental Learning
Yanan Wu, Tengfei Liang, Songhe Feng, Yi Jin, Gengyu Lyu, Haojun Fei, Yang Wang
AAAI Conference on Artificial Intelligence (AAAI), 2023:10408-10416.

Beyond Word Embeddings: Heterogeneous Prior Knowledge Driven Multi-Label Image Classification
Xiang Deng, Songhe Feng, Gengyu Lyu, Hongzhe Liu, Yi Jin
IEEE Transactions on Multimedia (TMM), 25:4013-4025, 2023. [PDF]

Distance-Preserving Embedding Adaptive Bipartite Graph Multi-View Learning with Application to Multi-Label Classification
Xun Lu, Songhe Feng, Gengyu Lyu, Yi Jin, Congyan Lang
ACM Transactions on Knowledge Discovery from Data (TKDD), 17(2):19, 2023. [PDF]

ONION: Joint Unsupervised Feature Selection and Robust Subspace Extraction for Graph-Based Multi-View Clustering
Zhibin Gu, Songhe Feng, Ruiting Hu,Gengyu Lyu
ACM Transactions on Knowledge Discovery from Data (TKDD), 17(5):70, 2023. [PDF]

2022

Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning
Gengyu Lyu*, Xiang Deng*(Equal Contributions), Yanan Wu, Songhe Feng
AAAI Conference on Artificial Intelligence (AAAI), 2022:7647-7654 [PDF] [Codes]

Deep Graph Matching for Partial Label Learning
Gengyu Lyu*, Yanan Wu*(Equal Contributions), Songhe Feng
International Joint Conference on Artificial Intelligence (IJCAI), 2022:3306-3312 [PDF] [Codes]

A Self-Paced Regularization Framework for Partial Label Learning
Gengyu Lyu, Songhe Feng, Tao Wang, Congyan Lang
IEEE Transactions on Cybernetics (TCYB), 52(2):899-911, 2022. [PDF]

Global-Local Label Correlation for Partial Multi-Label Learning
Lijuan Sun, Songhe Feng, Jun Liu, Gengyu Lyu, Congyan Lang
IEEE Transactions on Multimedia (TMM), 24:581-593, 2022 [PDF]

2021

GM-PLL: Graph Matching based Partial Label Learning
Gengyu Lyu, Songhe Feng, Tao Wang, Congyan Lang, Yidong Li
IEEE Transactions on Knowledge and Data Engineering (TKDE), 33(2):521-535, 2021. [PDF] [Codes]

Noisy Label Tolerance: A New Perspective of Partial Multi-Label Learning
Gengyu Lyu, Songhe Feng, Yidong Li
Information Sciences (INS), 543:454-466, 2021. [PDF] [Codes]

GM-MLIC: Graph Matching based Multi-Label Image Classification
Yanan Wu, He Liu, Songhe Feng, Yi Jin, Gengyu Lyu, Zizhang Wu
International Joint Conference on Artificial Intelligence (IJCAI), 2021:1179-1185 [PDF]

2020

Partial Multi-Label Learning via Probabilistic Graph Matching Mechanism
Gengyu Lyu, Songhe Feng, Yidong Li
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (ACM SIGKDD), 2020:105-113 [PDF] [Codes]

HERA: Partial Label Learning by Combining Heterogeneous Loss with Sparse and Low-rank Regularization
Gengyu Lyu, Songhe Feng, Yidong Li, Yi Jin, Guojun Dai, Congyan Lang
ACM Transactions on Intelligent Systems and Technology (ACM TIST), 11(3):34, 1-19, 2020. [PDF]

Partial Label Learning via Self-Paced Curriculum Strategy
Gengyu Lyu, Songhe Feng, Yidong Li
The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2020:489-505

Partial Label Learning via Low-Rank Representation and Label Propagation
Gengyu Lyu, Songhe Feng, Wenying Huang, Guojun Dai
Soft Computing (SOCO), 24(7):5165-5176, 2020. [PDF]

Partial Multi-Label Learning via Multi-Subspace Representation
Ziwei Li*, Gengyu Lyu*(Equal Contributions), Songhe Feng
International Joint Conference on Artificial Intelligence (IJCAI), 2020:2612-2618 [PDF]

Partial Label Learning via Subspace Representation and Global Disambiguation
Yue Sun*, Gengyu Lyu*(Equal Contributions), Songhe Feng
The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2020:439-454


Students

  • Doctorate Students:
    2023 : Qiuru Hai (海秋茹), Yuena Lin (林约拿)
  • Graduate Students:
    2023 : Qiyu Zhong (钟淇宇), Weiqi Kang (康玮琦), Bohang Sun (孙博航)
    2024 : Hao Wei (魏浩)
  • Undergraduate Students:
    2020 : Hongdao Meng (孟宏道), Ziyu Zhou (周子渔)
    2021 : Yiyuan Wang (王逸远)
    2022 : Yakun Hu (胡娅坤)
    2022 : Zhiyuan Ma (马志远), Jialin Ge (葛佳林)
  • Alumni:
    2023 : Qiyu Zhong (北京工业大学,攻读硕士)

Teachings

  • Technologies of Weakly Supervised Machine Learning, Beijing University of Technology, Spring, (for graduate students), 2024.

Patents

  • Noisy Label Tolerance based Partial Multi-Label Learning Algorithm (No. CN111581468A)
  • Graph Matching based Non-Aligned Multi-View Multi-Label Learning Algorithm (No. 202311195295.8)
  • Deep Feature Graph Fusion based Multi-View Multi-Label Learning Algorithm (No. 202311116407.6)
  • Data Privacy Preserving based Multi-Modal Information Fusion Algorithm (No. 202311195296.2)

Selected Projects

  • Research on Key Technologies of Multi-View Multi-Label Learning under Non Perfect Data, National Natural Science Foundation of China, PI, 2024.01-2026.12
  • Research on Multi-View Information Fusion and Multi-Label Classification Algorithm, Project funded by China Postdoctoral Science Foundation, PI, 2023.01-2024.07
  • Research on Technologies of Public Sentiment Dissemination and Effectiveness Evaluation across Social Media Networks, National Key Research and Development Program of China, 2023.12-2026.11
  • Research on Key Issues of Graph Neural Networks for Relational Reasoning, National Natural Science Foundation of China, 2021.01-2024.12
  • Research on Key Technologies for Visual Saliency Analysis and Semantic Segmentation of Images under Weak Supervised Learning Framework, National Natural Science Foundation of China, 2021.01-2024.12
  • Research on Complex Scene based Unsupervised Transfer Learning Person Re-Identification Method, National Natural Science Foundation of China, 2020.01-2023.12
  • Research on Key Technologies of Large-Scale Image Semantic Understanding Under Weak Supervised Learning Framework, National Natural Science Foundation of China, 2019-2022
  • Research on Weakly Supervised Multi-Label Learning Algorithm and its Application in Image Semantic Understanding, Beijing Natural Science Foundation, 2020-2022
  • Research on Key Technologies for Image Saliency Detection and Segmentation under Weak Supervised Learning Framework, Beijing Natural Science Foundation, 2020-2022

Professional Activities

Reviewer for Journals

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Cybernetics (TCYB)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • IEEE Transactions on Industrial Informatics (TII)
  • Machine Learning (MLJ)
  • Pattern Recognition (PR)
  • Information Sciences (INS)
  • Neurocomputing
  • Chinese Journal of Electronics
  • 中国科学:信息科学
  • 软件学报

Reviewer for Conferences

  • International Conference on Learning Representations (ICLR 2022- )
  • International Conference on Machine Learning (ICML 2021- )
  • Conference on Neural Information Processing Systems (NeurIPS 2021- )
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021- )
  • International Conference on Computer Vision (ICCV 2021- )
  • European Conference on Computer Vision (ECCV 2022- )
  • AAAI Conference on Artificial Intelligence (AAAI 2021- )
  • International Joint Conference on Artificial Intelligence (IJCAI 2022- )