Zhirong Yang 杨志荣

Professor Norwegian Open AI Lab Department of Computer Science, Norwegian University of Science and Technology (NTNU) Office: IT-Bygget 320, Gløshaugen Postal Address: NTNU Department of Computer Science NO-7491 Trondheim, Norway Telephone: +47 901 54 911 E-mail:

Research Interests

Teaching

• TDT4173 Machine Learning
• TDT05 Self-Supervised Machine Learning

Software

• ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths
• Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks (CDIL)
• Parametrize Mixing Links in Sparse Factors for Self Attention (Paramixer)
• Sparse factorization of square matrices with application to neural attention modeling (PSF-Attn)
• Scalable Optimization of Neighbor Embedding for Visualization (NE)
• Clustering by Nonnegative Matrix Factorization Using Graph Random Walk (NMFR)
• Clustering by Low-Rank Doubly Stochastic Matrix Decomposition (DCD)
• Automatic Rank Determination in Projective Nonnegative Matrix Factorization (ARDPNMF)
• Projective Nonnegative Matrix Factorization (PNMF)
• Heavy-tailed Symmetric Stochastic Neighbor Embedding (HSSNE)

Selected Publications [Click to see full publication list]

• Ruslan Khalitov, Tong Yu, Lei Cheng, and Zhirong Yang. ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length. In International Conference on Learning Representations (ICLR) 2023. [paper][code]
• Lei Cheng, Ruslan Khalitov, Tong Yu, and Zhirong Yang. Classification of long sequential data using circular dilated convolutional neural networks. In Neurocomputing 2023. [paper][arXiv][code]
• Tong Yu, Ruslan Khalitov, Lei Cheng, and Zhirong Yang. Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better Than Dot-Product Self-Attention. In Computer Vision and Pattern Recognition Conference (CVPR) 2022. [paper][arXiv][code]
• Ruslan Khalitov, Tong Yu, Lei Cheng, and Zhirong Yang. Sparse factorization of square matrices with application to neural attention modeling. Neural Networks, vol. 152, pages 160-168, 2022 [paper][arXiv][code]
• K. Abudahab, J. Prada, Zhirong Yang, S. Bentley, N. Croucher, J. Corander, D. Anensen. PANINI: Pangenome Neighbour Identification for Bacterial Populations. Microbial Genomics 5(4): 1-10 (2018) [pdf].
• C. Chewapreecha, M. Holden, M. Vehkala, N. Välimäki, Zhirong Yang et al. Global and regional dissemination and evolution of Burkholderia pseudomallei. Nature Microbiology 2, 16263 (2017) [online version].
• Zhirong Yang, Jukka Corander and Erkki Oja. Low-Rank Doubly Stochastic Matrix Decomposition for Cluster Analysis. Journal of Machine Learning Research, 17(187): 1-25, 2016. [pdf]
• Zhirong Yang, Jaakko Peltonen and Samuel Kaski. Majorization-Minimization for Manifold Embedding. In AISTATS 2015. [pdf] [supplemental] [codes]
  
• Onur Dikmen, Zhirong Yang, Erkki Oja. Learning the Information Divergence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(7): 1442-1454, 2015. [preprint] [final pdf]
  
• Zhirong Yang, Jaakko Peltonen and Samuel Kaski. Optimization Equivalence of Divergences Improves Neighbor Embedding. In ICML 2014. [pdf] [supplemental] [codes]
  
• He Zhang, Zhirong Yang and Erkki Oja. Improving Cluster Analysis by Co-initializations. Pattern Recognition Letters, 45: 71-77, 2014. [preprint] [final pdf] [supplemental document] [Datasets and Matlab codes]
  
• Zhirong Yang, Jaakko Peltonen and Samuel Kaski. Scalable Optimization of Neighbor Embedding for Visualization. In ICML 2013. [pdf] [supplemental] [codes]
  
• Zhirong Yang, Tele Hao, Onur Dikmen, Xi Chen, Erkki Oja. Clustering by Nonnegative Matrix Factorization Using Graph Random Walk. In NIPS 2012. [pdf] [codes] [supplemental document]
  
• Zhirong Yang and Erkki Oja. Clustering by Low-Rank Doubly Stochastic Matrix Decomposition. In ICML 2012. [pdf] [codes] Pattern Recognition. 45(4): 1500-1510, 2012. [preprint] [final pdf on publisher pages]
  
• Zhirong Yang and Erkki Oja. Unified Development of Multiplicative Algorithms for Linear and Quadratic Nonnegative Matrix Factorization. IEEE Transactions on Neural Networks. 22(12): 1878-1891, 2011. [preprint] [final pdf on publisher pages]
  
• Zhirong Yang and Erkki Oja. Linear and Nonlinear Projective Nonnegative Matrix Factorization. In IEEE Transactions on Neural Networks, 21(5):734-749, 2010. [preprint] [final pdf on publisher pages] [codes]
  
• Zhirong Yang, Irwin King, Zenglin Xu, and Erkki Oja. Heavy-Tailed Symmetric Stochastic Neighbor Embedding. In NIPS 2009 (spotlight). [pdf] [codes]
  
• Zhirong Yang and Jorma Laaksonen. Principal Whitened Gradients for Information Geometry. Neural Networks, 21(2-3):232-240, 2008 [final pdf on publisher pages] [reprint pdf]
  
• Zhirong Yang and Jorma Laaksonen. Multiplicative updates for non-negative projections. Neurocomputing, 2007, 71(1-3):363-373. [final pdf on publisher pages] [reprint pdf]