Dr Tongliang Liu

BEng (USTC) PhD (UTS)
Lecturer
Statistical Learning Theory and Machine Learning
School of Information Technologies

J12 - The School of Information Technologies
The University of Sydney

Telephone +61 2 8627 5966

Website Personal site

School of Information Technologies

Biographical details

Tongliang Liu is a Lecturer in machine learning at the School of Information Technologies, The University of Sydney. He received the BEng degree in electronic engineering and information science from the University of Science and Technology of China, and the PhD degree from the University of Technology Sydney. From October 2015 to March 2016, he was a visiting PhD student with Barcelona Graduate School of Economics (Barcelona GSE) and the Department of Economics at Pompeu Fabra University, Spain. Prior to joining The University of Sydney, he was a Lecturer at the University of Technology Sydney.

His research interests lie in providing mathematical and theoretical foundations to justify and further understand machine learning models and designing efficient learning algorithms for problems in computer vision and data mining, with a particular emphasis on matrix factorisation, transfer learning, multi-task learning, and learning with label noise.

Research interests

In our daily lives, we make many decisions. Some are simple, but some are not. Why not let machines help? This is the principle underlying Dr Tongliang Liu's research into machine learning. He designs effective, efficient, and understandable learning algorithms - the processes machines use to "think" through datasets in order to "decide" how to respond to a problem.

"Machine learning is similar to human learning. As humans, when we encounter a problem, we think through our store of learned experience and knowledge to identify a rule that we think will apply to this situation, and we base our decision on that.

"Similarly, in machine learning, a machine presented with a problem will run algorithms ('think') through data ('experience and knowledge') to identify an applicable hypothesis ('rule'), and base its response ('decision') on that.

"My research aims to provide mathematical justifications for existing learning algorithms, and to design more effective and efficient learning algorithms for real-world problems in data mining and computer vision.

"For example, as we humans get older and gain more experience and knowledge, the decisions we make become more reliable. A similar phenomenon applies to machine learning as the amount of data collected increases. My research focuses on understanding this process, and how we can exploit it to make machine-made decisions more reliable.

"The ultimate goal would be to make machines as clever as humans. If we can develop machines that have even some of the decision-making capabilities of humans, this could reduce human labour and inconvenience and improve our quality of life. This is what motivates me to do research in machine learning.

"What excites me about this field is that recently some machine-learning algorithms have outperformed humans in several difficult problems, such as face recognition and playing the board game Go.

"I have been working in this field since 2012, and joined the University of Sydney in early 2017. The outstanding research staff and students here inspire me enormously. I believe that together we can achieve great things."

Awards and honours

  • Distinguished Paper Candidate - International Joint Conference on Artificial Intelligence (IJCAI) 2017
  • IEEE Transactions on Cybernetics Outstanding Reviewer - IEEE 2016
  • Best Paper Candidate - IEEE International Conference on Multimedia & Expo (ICME) 2014
  • Best Paper Award - IEEE International Conference on Information Science & Tech (ICIST) 2014
  • Computational Statistics & Data Analysis Outstanding Reviewer - ELSEVIER 2014

Selected publications

Download citations: PDF RTF Endnote

Journals

  • Liu, T., Tao, D., Song, M., Maybank, S. (2017). Algorithm-Dependent Generalization Bounds for Multi-Task Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(2), 227-241. [More Information]
  • Ma, K., Liu, W., Liu, T., Wang, Z., Tao, D. (2017). dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs. IEEE Transactions on Image Processing, 26(8), 3951-3964. [More Information]
  • Liu, Q., Sun, Y., Wang, C., Liu, T., Tao, D. (2017). Elastic net hypergraph learning for image clustering and semi-supervised classification. IEEE Transactions on Image Processing, 26(1), 452-463. [More Information]
  • Zhang, Y., Du, B., Zhang, L., Liu, T. (2017). Joint Sparse Representation and Multitask Learning for Hyperspectral Target Detection. IEEE Transactions on Geoscience and Remote Sensing, 55(2), 894-906. [More Information]
  • Liu, T., Gong, M., Tao, D. (2017). Large-Cone Nonnegative Matrix Factorization. IEEE Transactions on Neural Networks and Learning Systems, 28(9), 2129-2141. [More Information]
  • Liu, H., Wu, J., Liu, T., Tao, D., Fu, Y. (2017). Spectral Ensemble Clustering via Weighted K-means: Theoretical and Practical Evidence. IEEE Transactions On Knowledge And Data Engineering, 29(5), 1129-1143. [More Information]
  • Gui, J., Liu, T., Sun, Z., Tao, D., Tan, T. (2017). Supervised Discrete Hashing with Relaxation (Forthcoming). IEEE Transactions on Neural Networks and Learning Systems, 23. [More Information]
  • Liu, T., Tao, D. (2016). Classification with Noisy Labels by Importance Reweighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(3), 447-461. [More Information]
  • Liu, T., Tao, D., Xu, D. (2016). Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes. Neural Computation, 28(10), 2213-2249. [More Information]
  • Xiong, H., Liu, T., Tao, D., Shen, H. (2016). Dual Diversified Dynamical Gaussian Process Latent Variable Model for Video Repairing. IEEE Transactions on Image Processing, 25(8), 3626-3637. [More Information]
  • Xu, C., Liu, T., Tao, D., Xu, C. (2016). Local Rademacher Complexity for Multi-Label Learning. IEEE Transactions on Image Processing, 25(3), 1495-1507. [More Information]
  • Liu, T., Tao, D. (2016). On the performance of Manhattan nonnegative matrix factorization. IEEE Transactions on Neural Networks and Learning Systems, 27(9), 1851-1863. [More Information]
  • Gui, J., Liu, T., Tao, D., Sun, Z., Tan, T. (2016). Representative Vector Machines: A Unified Framework for Classical Classifiers. IEEE Transactions on Cybernetics, 46(8), 1877-1888. [More Information]
  • Li, X., Liu, T., Deng, J., Tao, D. (2016). Video face editing using temporal-spatial-smooth warping. ACM Transactions on Intelligent Systems and Technology, 7(3), 1-28. [More Information]
  • Gong, C., Liu, T., Tao, D., Fu, K., Tu, E., Yang, J. (2015). Deformed Graph Laplacian for Semisupervised Learning. IEEE Transactions on Neural Networks and Learning Systems, 26(10), 2261-2274. [More Information]
  • Luo, Y., Liu, T., Tao, D., Xu, C. (2015). Multiview matrix completion for multilabel image classification. IEEE Transactions on Image Processing, 24(8), 2355-2368. [More Information]
  • Lu, Y., Xie, F., Liu, T., Jiang, Z., Tao, D. (2015). No Reference Quality Assessment for Multiply-Distorted Images Based on an Improved Bag-of-Words Model. IEEE Signal Processing Letters, 22(10), 1811-1815. [More Information]
  • Luo, Y., Liu, T., Tao, D., Xu, C. (2014). Decomposition-based transfer distance metric learning for image classification. IEEE Transactions on Image Processing, 23(9), 3789-3801. [More Information]

Conferences

  • Liu, T., Lugosi, G., Neu, G., Tao, D. (2017). Algorithmic stability and hypothesis complexity. The 34th International Conference on Machine Learning, (ICML 2017). Proceedings of Machine Learning Research.
  • Luo, Y., Wen, Y., Liu, T., Tao, D. (2017). General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer. 26th International Joint Conference on Artificial Intelligence (IJCAI-17), Melbourne: International Joint Conferences on Artificial Intelligence.
  • Yu, X., Liu, T., Wang, X., Tao, D. (2017). On Compressing Deep Models by Low Rank and Sparse Decomposition. 2017 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2017), Piscataway: IEEE.
  • Liu, T., Yang, Q., Tao, D. (2017). Understanding How Feature Structure Transfers in Transfer Learning. 26th International Joint Conference on Artificial Intelligence (IJCAI-17), Melbourne: International Joint Conferences on Artificial Intelligence.
  • Xiong, H., Liu, T., Tao, D. (2016). Diversified Dynamical Gaussian Process Latent Variable Model for Video Repair. 30th AAAI Conference on Artificial Intelligence (AAAI 2016), United States: AAAI Press.
  • Gong, M., Zhang, K., Liu, T., Tao, D., Glymour, C., Scholkopf, B. (2016). Domain Adaptation with Conditional Transferable Components. 33rd International Conference on Machine Learning (ICML 2016), New York: Journal of Machine Learning Research (JMLR).
  • Li, Y., Tian, X., Liu, T., Tao, D. (2015). Multi-task model and feature joint learning. 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires: AAAI Press.
  • Liu, H., Liu, T., Wu, J., Tao, D., Fu, Y. (2015). Spectral ensemble clustering. The 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2015), New York: Association for Computing Machinery (ACM). [More Information]
  • Shao, M., Li, S., Liu, T., Tao, D., Huang, T., Fu, Y. (2014). Learning relative features through adaptive pooling for image classification. 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014), Piscataway, New Jersey: IEEE. [More Information]
  • Liu, T., Tao, D. (2014). On the robustness and generalization of Cauchy regression. 2014 4th IEEE International Conference on Information Science and Technology (ICIST 2014), Piscataway: IEEE. [More Information]

2017

  • Liu, T., Tao, D., Song, M., Maybank, S. (2017). Algorithm-Dependent Generalization Bounds for Multi-Task Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(2), 227-241. [More Information]
  • Liu, T., Lugosi, G., Neu, G., Tao, D. (2017). Algorithmic stability and hypothesis complexity. The 34th International Conference on Machine Learning, (ICML 2017). Proceedings of Machine Learning Research.
  • Ma, K., Liu, W., Liu, T., Wang, Z., Tao, D. (2017). dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs. IEEE Transactions on Image Processing, 26(8), 3951-3964. [More Information]
  • Liu, Q., Sun, Y., Wang, C., Liu, T., Tao, D. (2017). Elastic net hypergraph learning for image clustering and semi-supervised classification. IEEE Transactions on Image Processing, 26(1), 452-463. [More Information]
  • Luo, Y., Wen, Y., Liu, T., Tao, D. (2017). General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer. 26th International Joint Conference on Artificial Intelligence (IJCAI-17), Melbourne: International Joint Conferences on Artificial Intelligence.
  • Zhang, Y., Du, B., Zhang, L., Liu, T. (2017). Joint Sparse Representation and Multitask Learning for Hyperspectral Target Detection. IEEE Transactions on Geoscience and Remote Sensing, 55(2), 894-906. [More Information]
  • Liu, T., Gong, M., Tao, D. (2017). Large-Cone Nonnegative Matrix Factorization. IEEE Transactions on Neural Networks and Learning Systems, 28(9), 2129-2141. [More Information]
  • Yu, X., Liu, T., Wang, X., Tao, D. (2017). On Compressing Deep Models by Low Rank and Sparse Decomposition. 2017 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR 2017), Piscataway: IEEE.
  • Liu, H., Wu, J., Liu, T., Tao, D., Fu, Y. (2017). Spectral Ensemble Clustering via Weighted K-means: Theoretical and Practical Evidence. IEEE Transactions On Knowledge And Data Engineering, 29(5), 1129-1143. [More Information]
  • Gui, J., Liu, T., Sun, Z., Tao, D., Tan, T. (2017). Supervised Discrete Hashing with Relaxation (Forthcoming). IEEE Transactions on Neural Networks and Learning Systems, 23. [More Information]
  • Liu, T., Yang, Q., Tao, D. (2017). Understanding How Feature Structure Transfers in Transfer Learning. 26th International Joint Conference on Artificial Intelligence (IJCAI-17), Melbourne: International Joint Conferences on Artificial Intelligence.

2016

  • Liu, T., Tao, D. (2016). Classification with Noisy Labels by Importance Reweighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(3), 447-461. [More Information]
  • Liu, T., Tao, D., Xu, D. (2016). Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes. Neural Computation, 28(10), 2213-2249. [More Information]
  • Xiong, H., Liu, T., Tao, D. (2016). Diversified Dynamical Gaussian Process Latent Variable Model for Video Repair. 30th AAAI Conference on Artificial Intelligence (AAAI 2016), United States: AAAI Press.
  • Gong, M., Zhang, K., Liu, T., Tao, D., Glymour, C., Scholkopf, B. (2016). Domain Adaptation with Conditional Transferable Components. 33rd International Conference on Machine Learning (ICML 2016), New York: Journal of Machine Learning Research (JMLR).
  • Xiong, H., Liu, T., Tao, D., Shen, H. (2016). Dual Diversified Dynamical Gaussian Process Latent Variable Model for Video Repairing. IEEE Transactions on Image Processing, 25(8), 3626-3637. [More Information]
  • Xu, C., Liu, T., Tao, D., Xu, C. (2016). Local Rademacher Complexity for Multi-Label Learning. IEEE Transactions on Image Processing, 25(3), 1495-1507. [More Information]
  • Liu, T., Tao, D. (2016). On the performance of Manhattan nonnegative matrix factorization. IEEE Transactions on Neural Networks and Learning Systems, 27(9), 1851-1863. [More Information]
  • Gui, J., Liu, T., Tao, D., Sun, Z., Tan, T. (2016). Representative Vector Machines: A Unified Framework for Classical Classifiers. IEEE Transactions on Cybernetics, 46(8), 1877-1888. [More Information]
  • Li, X., Liu, T., Deng, J., Tao, D. (2016). Video face editing using temporal-spatial-smooth warping. ACM Transactions on Intelligent Systems and Technology, 7(3), 1-28. [More Information]

2015

  • Gong, C., Liu, T., Tao, D., Fu, K., Tu, E., Yang, J. (2015). Deformed Graph Laplacian for Semisupervised Learning. IEEE Transactions on Neural Networks and Learning Systems, 26(10), 2261-2274. [More Information]
  • Li, Y., Tian, X., Liu, T., Tao, D. (2015). Multi-task model and feature joint learning. 24th International Joint Conference on Artificial Intelligence (IJCAI 2015), Buenos Aires: AAAI Press.
  • Luo, Y., Liu, T., Tao, D., Xu, C. (2015). Multiview matrix completion for multilabel image classification. IEEE Transactions on Image Processing, 24(8), 2355-2368. [More Information]
  • Lu, Y., Xie, F., Liu, T., Jiang, Z., Tao, D. (2015). No Reference Quality Assessment for Multiply-Distorted Images Based on an Improved Bag-of-Words Model. IEEE Signal Processing Letters, 22(10), 1811-1815. [More Information]
  • Liu, H., Liu, T., Wu, J., Tao, D., Fu, Y. (2015). Spectral ensemble clustering. The 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2015), New York: Association for Computing Machinery (ACM). [More Information]

2014

  • Luo, Y., Liu, T., Tao, D., Xu, C. (2014). Decomposition-based transfer distance metric learning for image classification. IEEE Transactions on Image Processing, 23(9), 3789-3801. [More Information]
  • Shao, M., Li, S., Liu, T., Tao, D., Huang, T., Fu, Y. (2014). Learning relative features through adaptive pooling for image classification. 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW 2014), Piscataway, New Jersey: IEEE. [More Information]
  • Liu, T., Tao, D. (2014). On the robustness and generalization of Cauchy regression. 2014 4th IEEE International Conference on Information Science and Technology (ICIST 2014), Piscataway: IEEE. [More Information]

For support on your academic profile contact .