Qian Li is currently a Postdoc Research Fellow at University of Technology Sydney. She received her Ph.D. in Computer Science from Chinese Academy of Sciences in 2017. She obtained her Master degrees from Shandong University, China in 2012. Her research interests lie primarily in causal analysis, optimization algorithms and interpretable machine learning.
She has published several papers in high-impact conferences including CVPR, AAAI, WWW, CIKM, PAKDD, etc., and Journal of Knowledge and Information Systems (KAIS), Neurocomputing, Journal of Network and Computer Applications (JNCA), Journal of Network and Systems Management (JNSM). She also serves as Program Committee Member and reviewers in well-known international conferences, including AAAI, IJCAI, KDD, PAKDD, CIKM, WWW, KSEM, and she is also invited as the reviewer for IEEE Transactions on Neural Networks and Learning Systems (TNNLS), and Concurrency and Computation: Practice and Experience (CCPE), International Journal of Intelligent Systems.
Can supervise: YES
© 2020 Elsevier B.V. Privileged information (PI), known as teacher providing students helpful comments, comparisons, and explanations to improve students' performance, has been widely applied in various machine learning tasks, resulting in great success. Existing approaches utilizing attributes either fail to leveraging the attributes information thoroughly, or suffer from the complex network structures for automatically attributes learning. Therefore, we propose a new Deep Convolutional Neural Network with Privileged Information (PI-DCNN) for photo aesthetic assessment by utilizing the prior knowledge of photo and photographic elements as privileged information. This paper is the first to systematically summarize all the attributes (i.e., photo and photographic attributes) related to aesthetics assessment. Specifically, we first explore the privileged information of photo and photography attributes, which is available at the training stage but it is not available for the test set. After that, we transfer the probabilistic dependency relations as constraints, and formulate photo aesthetics assessment in a deep convolutional neural network. Lastly, we propose a new pair-wise ranking loss that can exploit the relationship of photo aesthetic quality within a pair of photos. Experimental results on two widely benchmark databases of aesthetic assessment, AADB and AVA, demonstrate the effectiveness of the proposed PI-DCNN method on photo aesthetic assessment task.
Li, Q, Li, G, Niu, W, Cao, Y, Chang, L, Tan, J & Guo, L 2017, 'Boosting imbalanced data learning with Wiener process oversampling', Frontiers of Computer Science, vol. 11, no. 5, pp. 836-851.View/Download from: Publisher's site
Li, Q, Wang, Z, Li, G, Cao, Y, Xiong, G & Guo, L 2017, 'Learning Robust Low-Rank Approximation for Crowdsourcing on Riemannian Manifold', Procedia Computer Science, vol. 108, pp. 285-294.View/Download from: Publisher's site
Niu, W, Tong, E, Li, Q, Li, G, Wen, X, Tan, J & Guo, L 2016, 'Exploring probabilistic follow relationship to prevent collusive peer-to-peer piracy', Knowledge and Information Systems, vol. 48, no. 1, pp. 111-141.View/Download from: Publisher's site
Li, Q, Niu, W, Li, G, Tong, E, Hu, Y, Liu, P & Guo, L 2015, 'Recover Fault Services via Complex Service-to-Node Mappings in Wireless Sensor Networks', Journal of Network and Systems Management, vol. 23, no. 3, pp. 474-501.View/Download from: Publisher's site
Wang, Z, Li, Q, Li, G & Xu, G 2019, 'Polynomial representation for persistence diagram', Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, CA, USA, pp. 6116-6125.View/Download from: Publisher's site
© 2019 IEEE. Persistence diagram (PD) has been considered as a compact descriptor for topological data analysis (TDA). Unfortunately, PD cannot be directly used in machine learning methods since it is a multiset of points. Recent efforts have been devoted to transforming PDs into vectors to accommodate machine learning methods. However, they share one common shortcoming: the mapping of PDs to a feature representation depends on a pre-defined polynomial. To address this limitation, this paper proposes an algebraic representation for PDs, i.e., polynomial representation. In this work, we discover a set of general polynomials that vanish on vectorized PDs and extract the task-adapted feature representation from these polynomials. We also prove two attractive properties of the proposed polynomial representation, i.e., stability and linear separability. Experiments also show that our method compares favorably with state-of-the-art TDA methods.
Yin, J, Liu, S, Li, Q & Xu, G 2019, 'Prediction and Analysis of Rumour's Impact on Social Media', BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings, International Conference on Behavioral, Economic and Socio-Cultural Computing, IEEE, Beijing, China.View/Download from: Publisher's site
© 2019 IEEE. Rumour, as an important form of social communication, has been run through the whole evolutionary history of mankind. People maliciously disseminate rumours in order to increase awareness, slander others or cause panic, etc. To eliminate this issue, many researchers resort to detecting rumours on social media. However, rumour detection is not sufficient to eliminate the negative impact, which also requires official institutions to provide the refutations. In practice, the number of rumours on social media is too large, there is no need to refute some rumours with little or no concern. Therefore, we need to evaluate the impact of the rumours in advance. In this paper, we devise a rumour influence prediction model RISM (Rumour Impact on Social Media) based on a popular rumour intensity formula to predict the impact of a newborn rumour. Extensive numerical experiments are carried out on the real rumour data that are collected from Toutiao.com, which demonstrate the effectiveness of our proposed RISM model.
Fang, Z, Li, Q, Cao, Y, Zhang, Z, Zhang, D & Liu, Y 2019, 'Joint entity linking with deep reinforcement learning', The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, pp. 438-447.View/Download from: Publisher's site
© 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License. Entity linking is the task of aligning mentions to corresponding entities in a given knowledge base. Previous studies have highlighted the necessity for entity linking systems to capture the global coherence. However, there are two common weaknesses in previous global models. First, most of them calculate the pairwise scores between all candidate entities and select the most relevant group of entities as the final result. In this process, the consistency among wrong entities as well as that among right ones are involved, which may introduce noise data and increase the model complexity. Second, the cues of previously disambiguated entities, which could contribute to the disambiguation of the subsequent mentions, are usually ignored by previous models. To address these problems, we convert the global linking into a sequence decision problem and propose a reinforcement learning model which makes decisions from a global perspective. Our model makes full use of the previous referred entities and explores the long-term influence of current selection on subsequent decisions. We conduct experiments on different types of datasets, the results show that our model outperforms state-of-the-art systems and has better generalization performance.
Li, Q & Wang, Z 2017, 'Riemannian submanifold tracking on low-rank algebraic variety', Thirty-First AAAI Conference on Artificial Intelligence.
Li, Q, Niu, W, Li, G, Tan, J, Xiong, G & Guo, L 2016, 'Riemannian optimization with subspace tracking for low-rank recovery', 2016 International Joint Conference on Neural Networks (IJCNN), 2016 International Joint Conference on Neural Networks (IJCNN), IEEE.View/Download from: Publisher's site
Li, Q, Niu, W, Li, G, Cao, Y, Tan, J & Guo, L 2015, 'Lingo', Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15, the 24th ACM International, ACM Press.View/Download from: Publisher's site
Li, Q, Liu, S & Pan, Y 2012, 'A cooperative construction approach for SaaS applications', Proceedings of the 2012 IEEE 16th International Conference on Computer Supported Cooperative Work in Design (CSCWD), 2012 IEEE 16th International Conference on Computer Supported Cooperative Work in Design (CSCWD), IEEE.View/Download from: Publisher's site
Li, Q, Schaffer, P, Pang, J & Mauw, S 2012, 'Comparative Analysis of Clustering Protocols with Probabilistic Model Checking', 2012 Sixth International Symposium on Theoretical Aspects of Software Engineering, 2012 Sixth International Symposium on Theoretical Aspects of Software Engineering (TASE), IEEE.View/Download from: Publisher's site