Future Intelligence Research Lab

The Future Intelligence Research Lab produces next-generation AI algorithms that address the following emerging challenges:

• AI Security and Cyber Attacks (See three representative papers from our lab: [1], [2], [3].)

• AI Robustness with Multi-modal Data. (Three representative papers: [4], [5], [6].)

• Model Fairness with Data Imbalance. (Three representative papers: [7], [8], [9].)

Publications

Due to the popularity of Wei's name, the DBLP does not have an accurate record of his publications. His Google Scholar page is here.

• • Wenqian Mu, Jiyuan Liu, Yongshun Gong, Wei Liu, Haoliang Sun, Xiushan Nie, Yilong Yin, and Yu Zheng. GeM: Gaussian embeddings with Multi-hop graph transfer for next POI recommendation. In Neural Networks, 2025.

• • Yang An, Zhibin Li, Xiaoyu Li, Wei Liu, Xinghao Yang, Haoliang Sun, Meng Chen, Yu Zheng, and Yongshun Gong: Spatio-Temporal Multivariate Probabilistic Modeling for Traffic Prediction. In IEEE Transactions on Knowledge and Data Engineering. (TKDE), 2025.

• • Yunce Zhao, Wei Huang, Wei Liu and Xin Yao: Revealing Vulnerable Regions through Diverse Adversarial Examples. In Machine Learning  journal, 2025.

• • Da Cheng Gu and Wei Liu: Assessing Vulnerabilities in State-of-the-Art Large Language Models Through Hex Injection. In Proceedings of The Thirty-Nineth AAAI Conference on Artificial Intelligence. (AAAI 2025).

• • Yunce Zhao, Wei Huang, Wei Liu and Xin Yao: “Negatively Correlated Ensemble against Transfer Adversarial Attacks". In Pattern Recognition, (2025).

• • Cheng Yongkang, Mingjiang Liang, Shaoli Huang, Gaoge Han, Jifeng Ning and Wei Liu: Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audio. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025).

• • Han Gaoge, Mingjiang Liang, Tangjing Lei, Wei Liu and Shaoli Huang: ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025).

• • Mingjiang Liang, Cheng Yongkang, Shaoli Huang, Jifeng Ning and Wei Liu: RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior. In Proceedings of the 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025).

• • Zhen Zhao, Brian Kenneth Erickson, Shantanu Chakraborty and Wei Liu: DELA: Dual Embedding Using LSTM and Attention for Asset Tag Inference in Industrial Automation Systems. In Proceedings of the 37th Australasian Joint Conference on Artificial Intelligence (AJCAI 2024).

• • Linsey Pang, Amir Raffiee, Wei Liu and Keld Lundgaard: Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings. In Proceedings of the 2024 IEEE International Conference on Big Data (IEEE BigData 2024).

• • Huining Cui and Wei Liu: SecEval: A Security Evaluation Dataset for Large Language Models. In Proceedings of the 22nd Australiasia Data Science and Machine Learning Conference (AusDM 2024).

• • Yongfeng Zhang, Zhiwei Liu, Qingsong Wen, Linsey Pang, Wei Liu and Philip S Yu: AI Agent for Information Retrieval: Generating and Ranking. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024).

• • Shilu Yuan, Yongshun Gong, Meng Chen, Wenpeng Lu, Xinxin Zhang and Wei Liu: Exploring High-Order Gravity Centers For Origin-Destination Demand Prediction Via Unified Spatiotemporal Hypergragh. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024).

• • Cheng Yongkang, Mingjiang Liang, Shaoli Huang, Jifeng Ning and Wei Liu: ExpGest: Expressive Full-Body Gesture Generation Using Diffusion Model and Hybrid Audio-Text Guidance. In Proceedings of the 2024 IEEE Conference on Multimedia Expo (ICME 2024).

• • Yunce Zhao, Wei Huang, Wei Liu and Xin Yao: Ensemble of Intermediate-Level Attacks to Boost Adversarial Transferability. In Proceedings of the 31st International Conference on Neural Information Processing (ICONIP2024).

• • Tom Roth, Yansong Gao, Alsharifb Abuadbba, Suryab Nepal and Wei Liu: Token-modification adversarial attacks for natural language processing: A survey. In AI Communications, 2024.

• • Shilu Yuan, Dongfeng Li, Wei Liu, Meng Chen, Junjie Zhang, and Yongshun Gong: Fine-Grained Urban Flow Inference with Dynamic Multi-scale Representation Learning. In Proceedings of the 29th International Conference on Database Systems for Advanced Applications (DASFAA 2024).

• • Li-Chiao Wang, Wei Liu and Chung-Shou Liao: Incremental Random Forest for Unsupervised Learning. In Proceedings of the 2024 IEEE International Conference on Artificial Intelligence (CAI 2024).

• • Li-Chiao Wang, Wei Liu and Chung-Shou Liao: Developing Incremental Learning Models with Prototypes. In Proceedings of the 2024 IEEE International Joint Conference on Neural Network (IJCNN 2024).

• • Tao Zheng and Wei Liu: Orthogonal Synthesis: Data Augmentation for Multimodal Sentiment Analysis. In Proceedings of the 2024 IEEE International Joint Conference on Neural Network (IJCNN 2024).

• • Mingze Ni and Wei Liu: Reversible Jump Attack to Textual Classifiers with Modification Reduction. In Machine Learning  journal, 2024.

• • Xiaoyu Li, Yongshun Gong, Wei Liu, Yilong Yin, Yu Zheng, and Liqiang Nie: Dual-track Spatio-temporal Learning for Urban Flow Inference with Adaptive Normalization. In Artificial Intelligence  journal, 2024.

• • Mingze Ni, Zhensu Sun, and Wei Liu: Fraud’s Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process. In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024.

• • Mingjiang Liang, Shaoli Huang and Wei Liu: Dynamic Semantic Structure Distillation for Low-resolution Fine-grained Recognition. In Pattern Recognition, 2023.

• • Ruifeng Wang, Yuansheng Liu, Yongshun Gong, Wei Liu, Meng Chen, Yilong Yin, and Yu Zheng: Fine-grained Urban Flow Inference with Unobservable Data via Space-Time Attraction Learning. In Proceedings of the 23rd IEEE International Conference on Data Mining (ICDM 2023).

• • Yongshun Gong, Zhibin Li, Wei Liu, Xinkai Lu, Xinwang Liu, Ivor Tsang, and Yiling Yin: Missingness-pattern-adaptive Learning with Incomplete Data. In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2023.

• • Xin Chen, Dongliang Guo, Li Feng, Bo Chen, and Wei Liu: Compass+Ring: A Multimodal Menu to Improve Interaction Performance and Comfortability in One-handed Scenarios. In Proceedings of the 22nd IEEE International Symposium on Mixed and Augmented Reality (ISMAR 2023)

• • Xinghao Yang, Yongshun Gong, Weifeng Liu, James Bailey, Dacheng Tao, and Wei Liu: Semantic-Preserving Adversarial Text Attacks. In IEEE Transactions on Sustainable Computing (IEEE T-SUSC), 2023.

• • Aneesh Sreevallabh Chivukula, Xinghao Yang, Bo Liu, Wei Liu, and Wanlei Zhou: Adversarial Machine Learning - Attack Surfaces, Defence Mechanisms, Learning Theories in Artificial Intelligence. Springer Book, Springer International Publishing, 2023.

• • Linsey Pang, Kexin Xie, Yuxi Zhang, Damian Xu, and Wei Liu: Adversarial Active Learning with Guided BERT Feature Encoding. In Proceedings of The 26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2023).

• • Xinghao Yang, Weifeng Liu, and Wei Liu: Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition. In Proceedings of The 39th IEEE International Conference on Data Engineering (ICDE 2023).

• • Mingze Ni, Zhensu Sun and Wei Liu: Fraud’s Bargain Attacks to Textual Classifiers via Metropolis-Hasting Sampling. In Proceedings of The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023).

• • Jiyao Li and Wei Liu: Summarization Attack via Paraphrasing. In Proceedings of The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023).

• • Mingze Ni, Tianqing Zhu, Shui Yu, and Wei Liu: Attacking Neural Machine Translations via Hybrid Attention Learning. In Machine Learning  journal, 2022.

• • Linsey Pang, Wei Liu, Lingfei Wu, Kexin Xie, Stephen Guo, and Musen Wen: Applied Machine Learning Methods for Time Series Forecasting. In Proceedings of the 31st ACM Conference on Information and Knowledge Management. (CIKM 2022).

• • Linsey Pang, Wei Liu, Kexin Xie, James Bailey, Longbing Cao, and Yuxi Zhang: Deep Learning for Search and Recommendation. In Proceedings of the 31st ACM Conference on Information and Knowledge Management. (CIKM 2022).

• • Kam Fataliyev and Wei Liu: MMDL: A Novel Multi-modal Deep Learning Model for Stock Market Prediction. In Proceedings of the 2022 IEEE International Conference on Data Science and Advanced Analytics. (DSAA 2022).

• • Mingze Ni, Tianqing Zhu, Shui Yu, and Wei Liu: Attacking Neural Machine Translations via Hybrid Attention Learning. In Proceedings of the 2022 IEEE International Conference on Data Science and Advanced Analytics. (DSAA 2022).

• • Linsey Pang, Wei Liu, Keng-Hao Chang, and Moumita Bhattacharya: Deep Search Relevance Ranking in Practice. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (KDD 2022).

• • Abraham Bagherjeiran, Nemanja Djuric, Mihajlo Grbovic, Kuang-Chih Lee, Wei Liu, and Suju Rajan: AdKDD: Knowledge Discovery from Advertisement Data. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. (KDD 2022).

• • Tao Zhang, Sunny Verma, and Wei Liu: Interpretable Binaural Ratio for Visually Guided Binaural Audio Generation. In Proceedings of the 2022 International Joint Conference on Neural Networks. (IJCNN 2022).

• • Mingjiang Liang, Shaoli Huang, Shirui Pan, Mingming Gong, and Wei Liu: Learning Multi-level Weight-centric Features for Few-shot Learning. In Pattern Recognition, 2022.

• • Huan Tian, Tianqing Zhu, Wei Liu, and Wanlei Zhou: Image Fairness in Deep Learning: Problems, Models, and Challenges. In Neural Computing and Applications, 2022.

• • Hanyun Zhang, Dongliang Guo, Wei Liu, and Junlan Nie: An Improved Algorithm for Video Quality Assessment. In Multimedia Systems, 2022.

• • Lianbo Zhang, Shaoli Huang, and Wei Liu: Enhancing Mixture-of-Experts by Leveraging Attention for Fine-Grained Recognition. In IEEE Transactions on Multimedia, 2021.

• • Lei Hu, Shaoli Huang, Wei Liu, and Jifeng Ning: Do We Really Need Frame-by-Frame Annotation Datasets for Object Tracking? In Proceedings of The 29th ACM International Conference on Multimedia (MM 2021).

• • Lianbo Zhang, Shaoli Huang, and Wei Liu: Learning Sequentially Diversified Representations for Fine-grained Categorization. In Pattern Recognition, 2021.

• • Xinghao Yang, Weifeng Liu, Dacheng Tao, and Wei Liu: BESA: BERT-based Simulated Annealing for Adversarial Text Attacks. In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021).

• • Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, and Yu Zheng: Missing Value Imputation for Multi-view Urban Statistical Data via Spatial Correlation Learning. In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021.

• • Ali Braytee and Wei Liu: Learning Discriminative Features using Multi-label Dual Space. In Proceedings of the 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2021).

• • Sunny Verma, Chen Wang, Liming Zhu, and Wei Liu: Attn-HybridNet: Improving Discriminability of Hybrid Features with Attention Fusion. In IEEE Transactions on Cybernetics, 2021. (IF: 11.079).

• • Changwei Sung, Xinghao Yang, Chungshou Liao, and Wei Liu: IntRoute: An Integer Programming based Approach for Best Bus Route Discovery. In Proceedings of the 26th International Conference on Database Systems for Advanced Applications (DASFAA 2021).

• • Xinghao Yang, Weifeng Liu, James Bailey, Dacheng Tao, and Wei Liu: Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic Search. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021).

• • Xinghao Yang, Weifeng Liu, Shengli Zhang, Wei Liu, and Dacheng Tao: Targeted Attention Attack on Deep Learning Models in Road Sign Recognition. In IEEE Internet of Things Journal (IoT-J), 2021. IF: 9.936.

• • Xinghao Yang, Weifeng Liu, and Wei Liu: Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition. In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021.

• • Lianbo Zhang, Shaoli Huang, Wei Liu: Intra-class Part Swapping for Fine-Grained Image Classification. In Proceedings of the 2021 IEEE Winter Conference on Applications in Computer Vision (WACV 2021).

• • Sunny Verma, Fan Jin, Yang Wang, Fang Chen, and Wei Liu: Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis. In Proceedings of the 20th IEEE International Conference on Data Mining (ICDM 2020).

• • Yongshun Gong, Jian Zhang, and Wei Liu: A Spatial Missing Value Imputation Method for Multi-view Urban Statistical Data. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020).

• • Xinghao Yang and Wei Liu: Population Location and Movement Estimation through Cross-domain Data Analysis. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI 2020).

• • Yongshun Gong, Zhibin Li, Jian Zhang, Wei Liu, and Yu Zheng: Online Spatio-temporal Crowd Flow Distribution Prediction for Complex Metro System. In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020.

• • Aneesh Chivukula, Xinghao Yang, Tianqing Zhu, Wanlei Zhou, and Wei Liu: Game Theoretical Adversarial Deep Learning with Variational Adversaries. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020.

• • Xinghao Yang, Wei Liu, Wenfeng Liu, Dacheng Tao: A Survey on Canonical Correlation Analysis. In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020.

• • Xinghao Yang, and Wei Liu: Cyber Attack to AI Systems: Targeted Attention-based Attacks to Road Sign Recognition Models. In Proceedings of the 2020 Cyber Defence Next Generation Technology Conference (CDNG 2020).

• • Yongshun Gong, Wei Liu, Zhibin Li, and Jian Zhang: Potential Passenger Flow Prediction: A Novel Study for Urban Transportation Development. In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).

• • Aneesh Chivukula, Xianghao Yang, and Wei Liu: Adversarial Deep Learning with Stackelberg Games. In Proceedings of the 26th International Conference on Neural Information Processing (ICONIP 2019).

• • Lianbo Zhang, Shaoli Huang, Wei Liu, and Dacheng Tao: Learning a Mixture of Gradually Enhanced Experts for Fine-Grained Categorization. In Proceedings of the 2019 International Conference on Computer Vision (ICCV 2019).

• • Quan Do, Wei Liu, Jin Fan, and Dacheng Tao: Unveiling Hidden Implicit Similarities for Cross-Domain Recommendation. In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2019.

• • Sunny Verma, Chen Wang, Liming Zhu, and Wei Liu: Towards Effective Data Augmentation via Unbiased GAN Utilization. In Proceedings of the 16th Pacific Rim International Conference on Artificial Intelligence (PRICAI 2019).

• • Quan Do, Sunny Verma, and Wei Liu: Multiple Knowledge Transfer for Cross Domain Recommendation. In Proceedings of the 16th Pacific Rim International Conference on Artificial Intelligence (PRICAI 2019).

• • Sunny Verma, Chen Wang, Liming Zhu, and Wei Liu: DeepCU: Integrating both Common and Unique Latent Information for Multimodal Sentiment Analysis. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019).

• • Sunny Verma, Chen Wang, and Wei Liu: A Compliance Checking Framework for DNN Models. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019).

• • Ali Braytee, Wei Liu, and Paul Kennedy: Correlated Multi-label Classification with Incomplete Label Space and Class Imbalance. ACM Transactions on Intelligent Systems and Technology (ACM TIST), 2019. 5-year Impact Factor: 10.47.

• • Zhizhou Yin, Sanjay Chawla, and Wei Liu: Adversarial Attack and Defense with Deep Learning Frameworks. Book Chapter in Deep Learning for Cyber Security, Springer.

• • Yongshun Gong, Wei Liu, Jian Zhang, and Yu Zheng: Network-wide Crowd Flow Prediction of Sydney Trains via customized Online Non-negative Matrix Factorization. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM 2018).

• • Aneesh Chivukula and Wei Liu: Discovering Granger-causal Features from Deep Learning Networks. In Proceedings of the 31st Australasian Joint Conference on Artificial Intelligence (AI 2018).

• • Sunny Verma, Chen Wang, Liming Zhu, and Wei Liu: Improving Deep Learning Networks via Integrating Two Views of Images. In Proceedings of the 25th International Conference on Neural Information Processing (ICONIP 2018).

• • Aneesh Chivukula and Wei Liu: Adversarial Deep Learning Models with Multiple Adversaries, In IEEE Transactions on Knowledge and Data Engineering (TKDE). 2018. Impact Factor: 4.935

• • Quan Do and Wei Liu: Scalable Multimodal Factorization for Learning from Very Big Data, Book Chapter in Multimodal Analytics for Next-Generation Big Data Technologies and Applications, Springer

• • Pengyi Yang, John Ormerod, Wei Liu, and Albert Zomaya: AdaSampling for Positive-Unlabeled and Label Noise Learning with Bioinformatics Applications. In IEEE Transactions on Cybernetics. 2018. Impact Factor: 11.079.

• • Zhizhou Yin, Fei Wang, Wei Liu, and Sanjay Chawla: Sparse Feature Attacks in Adversarial Learning. In IEEE Transactions on Knowledge and Data Engineering (TKDE). 2018. Impact Factor: 3.438.

• • Shoujin Wang, Liang Hu, Longbing Cao, and Wei Liu: Attention-based Transactional Context Embedding for Next-Item Recommendation. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018).

• • Ali Braytee, Wei Liu, Daniel Catchpoole and Paul Kennedy: Multi-Label Feature Selection using Correlation Information. In Proceedings of the 26th ACM International Conference on Information and Knowledge Management (CIKM 2017).

• • Pengyi Yang, Wei Liu, and Jean Yang: Positive Unlabelled Learning via Wrapper-based Adaptive Sampling. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI 2017).

• • Quan Do, Wei Liu, Fang Chen: Discovering both Explicit and Implicit Similarities for Cross-Domain Recommendations. In Proceedings of the 2017 Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2017).

• • Aneesh Chivukula, and Wei Liu: Adversarial learning games with deep learning models. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN 2017).

• • Ali Braytee, Wei Liu, and Paul Kennedy: Supervised context-aware non-negative matrix factorization to handle high-dimensional high-correlated imbalanced biomedical data. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN 2017).

• • Sunny Verma, Wei Liu, Chen Wang, and Liming Zhu: Extracting Highly Effective Features for Supervised Learning via Simultaneous Tensor Factorization. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI 2017).

• • Ali Braytee, Wei Liu, Daniel Catchpoole, Paul Kennedy: Balanced Supervised Non-Negative Matrix Factorization for Childhood Leukaemia Analysis. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management (CIKM 2016).

• • Prasad Cheema, Khoa Nguyen, Wei Liu, et. al.: On Structural Health Monitoring Using Tensor Analysis and Support Vector Machine with Artificial Negative Data. In Proceedings of the 25th ACM International Conference on Information and Knowledge Management (CIKM 2016).

• • Quan Do, Thanh Pham, Wei Liu, and Kotagiri Ramamohanarao: WTEN: An Advanced Coupled Tensor Factorization Strategy for Learning from Imbalanced Data. In Proceedings of the 17th International Conference on Web Information Systems Engineering (WISE 2016).

• • Lida Rashidi, Andrey Kan, Wei Liu, James Bailey, Rao Kotagiri, et. al.: Node Re-Ordering for Anomaly Detection in Time Evolving Graphs. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML PKDD 2016).

• • Wei Liu: Factorization of Multiple Tensors for Supervised Feature Extraction. In Proceedings of the 23rd International Conference on Neural Information Processing. (ICONIP 2016).

• • Ali Braytee, Wei Liu, Paul Kennedy: A Cost-Sensitive Learning Strategy for Feature Extraction from Imbalanced Data. In Proceedings of the 23rd International Conference on Neural Information Processing. (ICONIP 2016).

• • Ling Luo, Wei Liu, Irena Koprinska, Fang Chen: A Discrimination-Aware Association Rule Classifier for Decision Support. In Transactions on Large Scale Data and Knowledge Centered Systems (Invited paper).

• • Quan Do and Wei Liu: ASTEN: an Accurate and Scalable Approach to Coupled Tensor Factorisation. In Proceedings of the 2016 International Joint Conference in Neural Networks (IJCNN 2016).

• • Shoujin Wang, Wei Liu, and Paul Kennedy: Training Deep Networks on Imbalanced Data Sets. In Proceedings of the 2016 International Joint Conference in Neural Networks (IJCNN 2016).

• • Hoang Nguyen, Wei Liu, Paul Rivera, and Fang Chen: TrafficWatch: Real-time Traffic Incident Detection and Monitoring Using Social Media. In Proceedings of the 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2016).

• • Hoang Nguyen, Wei Liu, and Fang Chen: Discovering Congestion Propagation Patterns in Spatio-Temporal Traffic Data. Accepted in IEEE Transactions on Big Data.

• • Jingyu Shao, Junfu Yin, Wei Liu, and Longbing Cao: Mining Actionable Combined Patterns Satisfying both Utility and Frequency Criteria. In Proceedings of the 2015 IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA 2015).

• • Qianqian Chen, Liang Hu, Jia Xu, Wei Liu, and Longbing Cao: Document Similarity Analysis via Involving both Explicit and Implicit Sematic Relatedness. In Proceedings of the 2015 IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA 2015).

• • Ling Luo, Wei Liu, Irena Koprinska, and Fang Chen: Discrimination-Aware Association Rule Mining for Unbiased Data Analytics. Book chapter in Big Data Analytics and Knowledge Discovery, 2015.

• • Ling Luo, Irena Koprinska and Wei Liu: Discrimination-Aware Classifiers for Student Performance Prediction. In Proceedings of the 8th International Conference on Educational Data Mining (EDM 2015).

• • Khoa Nguyen, Wei Liu, Fang Chen, Peter Runcie, et al.: Using Tensor Analysis for Damage Identification in Civil Structures. In Proceedings of the 19th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2015).

• • Xinxin Jiang, Wei Liu, Longbing Cao, Guodong Long: Coupled Collaborative Filtering for Context-aware Recommendation. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015).

• • Jingyu Shao, Junfu Yin, Wei Liu, Longbing Cao: Actionable Combined High Utility Itemset Mining. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015).

• • Fei Wang, Wei Liu, Sanjay Chawla: On Sparse Feature Attacks in Adversarial Learning. In Proceedings of the 2014 IEEE International Conference on Data Mining (ICDM 2014). (Acceptance rate: 19%)

• • Ronnie Taib, David Yee, Fang Chen, and Wei Liu: Improved incident management through anomaly detection in historical records. In 21st World Congress on Intelligent Transport Systems, ITSWC 2014: Reinventing Transportation in Our Connected World.

• • Wei Liu, Dong Lee, and Rao Kotagiri: Using Local Information to Significantly Improve Classification Performance. In proceedings of the 23rd ACM Conference on Information and Knowledge Management (CIKM 2014).

• • Victor Chu, Wei Liu, Raymond Wong, Fang Chen, and Charles Perng: Traffic Analysis as a Service via a Unified Model. In Proceedings of the 11th IEEE International Conference on Services Computing (IEEE SCC 2014).

• • Victor Chu, Wei Liu, Raymond Wong, and Fang Chen: Causal Structure Discovery for Spatio-temporal Data. In Proceedings of the 19th International Conference on Database Systems for Advanced Applications (DASFAA 2014).

• • Jeffrey Chan, Wei Liu, James Bailey, Christopher Leckie, and Rao Kotagiri: Structure-aware Distance Measures for Comparing Clusterings in Graphs. In Proceedings of the 18th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2014).

• • Wei Liu, James Bailey, Christopher Leckie, Fang Chen, and Rao Kotagiri: A Bayesian Classifier for Learning from Tensorial Data. In Proceedings of the 2013 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2013).

• • Wei Liu, James Bailey, Christopher Leckie, Fang Chen, and Rao Kotagiri: A Bayesian Classifier for Learning from Tensorial Data. In Proceedings of the 2013 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2013).

• • Timothy C. Havens, James C. Bezdek, Christopher Leckie, Wei Liu, James Bailey, and Kotagiri Ramamohanarao: Discrimination-aware classification for imbalanced datasets. In Proceedings of the 2013 IEEE International Conference on Fuzzy Systems. (FUZZ-IEEE 2013).

• • Jeffrey Chan, Wei Liu, James Bailey, Christopher Leckie, and Rao Kotagiri: Discovering Latent Blockmodels in Sparse and Noisy Graphs using Non-negative Matrix Factorisation. In Proceedings of the 22nd ACM Conference on Information and Knowledge Management (CIKM 2013).

• • Wei Liu, James Bailey, Christopher Leckie, Rao Kotagiri: Mining Labelled Tensors by Discovering both their Common and Discriminative Subspaces. In Proceedings of the 2013 SIAM Conference on Data Mining (SDM 2013).

• • Fei Wang, Wei Liu, and Sanjay Chawla: Tikhonov or Lasso Regularization: Which is Better and When. In Proceedings of the 2013 IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2013).

• • Goce Ristanoski, Wei Liu, and James Bailey: Time-Dependent Loss Enhanced SVMs for Time Series Regression. In Proceedings of the 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2013).

• • Wei Liu, Sanjay Chawla, James Bailey, Christopher Leckie and Rao Kotagiri: An Efficient Adversarial Learning Strategy for Constructing Robust Classification Boundaries. In Proceedings of the 25th Australasian Joint Conference on Artificial Intelligence (AI 2012). This paper won the best paper award.

• • Wei Liu, Jeffrey Chan, James Bailey, Christopher Leckie and Rao Kotagiri: Utilizing Common Substructures to Speedup Tensor Factorization for Mining Dynamic Graphs. In Proceedings of the 21st ACM Conference on Information and Knowledge Management (CIKM 2012).

• • Wei Liu, Andrey Kan, James Bailey, Christopher Leckie, Jian Pei and Rao Kotagiri: On Compressing Weighted Time-evolving Graphs. In Proceedings of the 21st ACM Conference on Information and Knowledge Management (CIKM 2012).

• • Linsey Pang, Sanjay Chawla, Wei Liu and Yu Zheng: On Detection of Emerging Anomalous Traffic Patterns Using GPS Data. Data & Knowledge Engineering journal, vol. 87, pages 357-373, 2013.

• • Goce Ristanoski, Wei Liu, James Bailey: Time Series Forecasting using Distribution Enhanced Linear Regression. In Proceedings of the 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2013).

• • Pengyi Yang, Wei Liu, Bingbing Zhou, Sanjay Chawla, Albert Zomaya: Ensemble-based wrapper methods for feature selection and class imbalance learning. In Proceedings of the 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2013).

• • Wei Liu and Sanjay Chawla: Mining Adversarial Patterns via Regularized Loss Minimization. Machine Learning, vol. 81, num. 1, pages 69-83.

• • Jeffrey Chan, Wei Liu, Christopher Leckie, James Bailey and Rao Kotagiri: SeqiBloc: Mining Multi-time Spanning Blockmodels in Dynamic Graphs. In Proceedings of the 18th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2012), pages 651–659.

• • Wei Liu, Yu Zheng, Sanjay Chawla, Jing Yuan and Xing Xie: Discovering Causal Interactions among Spatio-Temporal Outliers from Traffic Data Streams. In Proceedings of the 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2011), pages 1010–1018.

• • Linsey Xiaolin Pang, Sanjay Chawla, Wei Liu and Yu Zheng: On Mining Emerging Patterns on Traffic Networks. In Proceedings of the 7th International Conference on Advanced Data Mining and Applications (ADMA 2011). This paper won the best paper award.

• • Wei Liu and Sanjay Chawla: Class Confidence Weighted kNN Algorithms for Imbalanced Data Sets. In Proceedings of the 15th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2011), Part II, pages 345–356.

• • Wei Liu and Sanjay Chawla: A Quadratic Mean based Supervised Learning Model for Handling Data Skewness. In Proceedings of the 2011 SIAM International Conference on Data Mining (SDM 2011), pages 188–198.

• • Elizabeth Wu, Wei Liu, and Sanjay Chawla: Spatio-Temporal Outlier Detection in Precipitation Data. In Knowledge Discovery from Sensor Data, Springer, 2010.

• • Wei Liu and Sanjay Chawla: Mining Adversarial Patterns via Regularized Loss Minimization. In Proceedings of 2010 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2010) .

• • Wei Liu, Sanjay Chawla, David Cieslak and Nitesh Chawla: A Robust Decision Tree Algorithm for Imbalanced Data Sets. In Proceedings of the Tenth SIAM International Conference on Data Mining (SDM 2010), pages 766-777.

• • Wei Liu and Sanjay Chawla: A Game Theoretical Model for Adversarial Learning. In Proceedings of the 2009 IEEE ICDM Workshops 2009, pages 25-30.

Code Release

Our Lab releases open-source code corresponding to the AI theories and algorithms we have developed, such as:

• • SecEval: A Security Evaluation Dataset for Large Language Models



• • Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process



• • Hybrid Attentive Attacks to Neural Machine Translations



• • Reversible Jump Attack to Textual Classifiers.



• • BU-SPO: Semantic-preserving Adversarial Text Attacks.



• • FEIT Course Bot: a Chatbot that Answers all your Questions related to IT degrees at UTS.

• • BU-MHS: Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic Search.

• • TAA: Targeted Attention Attack on Deep Learning Models in Road Sign Recognition.



• • BESA: BERT-based Simulated Annealing for Adversarial Text Attacks.

• • TCCANet: Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition.

• • CDRec: the First Cross Domain Recommender based on Coupled Matrix Factorization Algorithm.

• • Deep-HOSeq: a Deep Higher-Order Sequence Fusion for Multimodal Sentiment Analysis Method.

• • DeepCU: for Integrating Both Common and Unique Latent Information for Multimodal Sentiment Analysis.

• • Deep-HOSeq: Deep Higher-Order Sequence Fusion for Multimodal Sentiment Analysis.

• • Attn-HybridNet: for Improving Discriminability of Hybrid Features with Attention Fusion.

• • LiST: a Lightning-fast and Scalable Coupled Tensor Factorization Method.

• • ASTEN: an Accurate and Scalable Approach to Coupled Tensor Factorization Method.

Research Grants and Industry Projects

Wei has been leading a number of nationally competitive grants and contract research projects funded by government agencies and industry organisations, spanning information security, digital media, retail, insurance, finance, transportation, and regulation sectors:

• • "Predicting Livestock Weight Gain: Leveraging Machine Learning to Improve Productivity for Australian Producers", Sole Chief Investigator; Project funder: Department of Education, 2024 - 2028.

• • "Foragecaster", Chief Investigator; Project funder: Agriwebb and Food Agility CRC, 2024 - 2027.

• • "Deep Learning Attacks and Active Defences: A Cybersecurity Perspective", Chief Investigator; Project funder: ARC Discovery Project, 2023 - 2026. This project received the special highlight in the ARC Media Release.

• • "Machine Learning for Agricultural Growth Prediction", Chief Investigator; Project funder: Agriwebb and Food Agility CRC, 2023.

• • "Knowledge Graphs for Process Monitoring and Control", Sole Chief Investigator; Project funder: AVEVA Software Australia Pty Ltd, 2022 - 2025.

• • "Skill and CV Data Analytics", Chief Investigator; Project funder: Reejig Pty Ltd, 2021 - 2022.

• • "Adversarial Learning in the Physical World", Sole Chief Investigator; Project funder: NSW Department of Industry, 2021 - 2022.

• • "Product Recommendation Systems with Multimodal Content Analysis", Sole Chief Investigator; Project funder: PINSPACE, 2021 - 2024.

• • "Defending AI Models again Adversarial Attacks", Sole Chief Investigator; Project funder: CSIRO's Data61, 2020 - 2023.

• • "Adversarial Learning for Feature Obfuscation", Sole Chief Investigator; Project funder: NSW Department of Industry, 2020 - 2021.

• • "Trajectory Data Mining", Sole Chief Investigator; Project funder: SUSTech, 2020-2021.

• • "Deep Learning in Finance", Sole Chief Investigator; Project funder: The RoZetta Institute, 2019 - 2021.

• • "Visual Computing and Big Data Research - Extension", Sole Chief Investigator; Project funder: HDU, 2019.

• • "Next Best Action Recommendations", Sole Chief Investigator; Project funder: FlightSpeed Tech, 2019.

• • "Learning from Multi-modal and Multi-source Data", Sole Chief Investigator; Project funder: SIEF, 2019.

• • "Product Recommendation Systems with Multimodal Content", Sole Chief Investigator; Project funder: Blackwoods, 2018.

• • "Visual Computing and Big Data Research - Extension", Sole Chief Investigator; Project funder: HDU, 2018.

• • "Visual Analytics for Digital Media", Sole Chief Investigator; UTS FEIT Data Arena Research Grant, 2018.

• • "Ad Recommender and Visualisation Tool", Lead Chief Investigator; Project funder: Assembly Media, 2017.

• • "Visual Computing and Big Data Research", Sole Chief Investigator; Project funder: HDU, 2017.

• • "Advanced Analytics to Reveal Novel Insights into ‘Worth of Water’", Chief Investigator; Project funder: NSW DPI, 2016.

• • "Advanced Data Analytics Platforms", Sole Chief Investigator; Project funder: National ICT Australia, 2016 – 2019.

• • "Data Analytics Models for Stock Market Surveillance", Sole Chief Investigator; Project funder: NASDAQ OMX and CMCRC, 2016 - 2019.

• • "Analytics Model to Support Strategic Planning", Sole Chief Investigator; Project funder: NSW Department of Fair Trading, 2015.

• • "Discovering Deep Insights Into Customer Retention", Chief Investigator; Project funder: Colonial Mutual, 2015.

• • "Transport Data Science and Advanced Analytics", Sole Chief Investigator; Project funder: National ICT Australia, 2015 – 2018.

• • "Large-scale Data Science Algorithms", Lead Chief Investigator; UTS Early Career Researcher Grant, 2015.

• • “Traffic Watch for Transport Control Service”, Chief Investigator; Project funder: Transport Management Centre, May 2013 – June 2014.

• • “Congestion Propagation and Hotspot Detection in Sydney CBD”, Chief Investigator; Project funder: NSW RMS; Aug – Dec 2013.

• • “Data Fusion Technologies for Comprehensive Transport Data Analysis in Melbourne”, Chief Investigator; Project funder: VicRoads; Jun – Sep 2013.

• • “Time of Arrival Estimations using HD Vehicle Trajectories”, Chief Investigator; Project funder: Tomtom. Jan 2013 – March 2013.

• • “Early Detection of Road Traffic Incidents using Social Media”, Chief Investigator; Project funder: the Transport Management Centre; Oct – Dec 2012.

• • “Causal Inference for Sequential Traffic Congestion", Chief Investigator; Project funder: Microsoft Research Asia; Nov 2010 – Mar 2011.

• • “Abnormal Claim Detection from Worker’s Compensations”, Chief Investigator; Project funder: CGU Insurance; Mar 2010 – Jun 2011.

• • “Data Integration for Cross-Market Capital Trading Systems”, Chief Investigator; Project funder: the SMARST Group, Jun 2008 – Dec 2009.

Research Team

Postdoc:

• • Mingze (Lucas) Ni

Current Students under my Principal Supervision:

• • Bonny Wang, PhD student, Robust AI Models for Defending Adversarial Attacks


• • Ayush Kanwal, PhD student, Leveraging Machine Learning to Improve Productivity for Australian Producers


• • Da Cheng Gu, MPhil student, Adversarial Attacks to Large Language Models


• • Akhilesh Singh, PhD student, Stocks Price Prediction using Deep Learning based Information Fusion


• • Huining Cui, PhD student, Safety Benchmarks for Large Language Models


• • Zhen Zhao, PhD student, Knowledge Graphs Learning for Process Monitoring and Control


• • Mingjiang Liang, PhD student, Few-Shot Image Classification


• • Jiyao Li, PhD student, Multimodal Sentiment Analysis

Graduated Students:

• • Kam Fataliyev, PhD student, Multimodal Machine Learning for Stock Price Prediction (First Job: Senior Data Scientist at PwC)


• • Mingze Ni, PhD student, Adversarial Attacks via Word-Level Manipulation on NLP Models (First Job: Postdoc at UTS)


• • Xinghao Yang, PhD student, Adversarial Machine Learning on AI Model Attacks (First Job: Associate Professor at China University of Petroleum)


• • Lianbo Zhang, PhD student, Improved Fine-Grained Representation Learning with Data Transformation


• • Maral Nalbandian, Honours student, AI-enabled Chatbot Development (First Job: Software Engineer at Commonwealth Bank)


• • Yongshun Gong, PhD student, Multiview Urban Computing (First Job: Associate Professor at Shandong University, China)


• • Xiaocai Zhang, PhD student, Deep Learning for Traffic Time Series Data Analysis (First Job: Postdoc Researcher at UTS)


• • Aneesh Chivukula, PhD student, Game theoretical adversarial deep learning algorithms (First Job: Assistant Professor at BITS, India)


• • Yuansheng Liu, PhD student, Data mining for high performance compression of genomic sequences (First Job: Postdoc Researcher at UTS)


• • Sunny Verma, PhD student, Feature extraction by data fusion (First Job: Postdoc Researcher at UTS)


• • Shoujin Wang, PhD student, Learning Complex Relations for Session-based Recommendations (First Job: Research Fellow at Macquarie University)


• • Quan Do, PhD student, Tensor-based data fusion analysis (First Job: Data Scientist at The ICONIC)


• • Ali Braytee, PhD student, Robust classification of high dimensional unbalanced single and multi-label datasets (First Job: Postdoc at UTS)


• • Ling Luo, PhD student, Causal inference for spatio-temporal data (First Job: Postdoc at CSIRO's Data61)


• • Xinxin Jiang, PhD student, on context-aware recommendation systems (First Job: Research Assistant at UTS)


• • Victor Chu, PhD student, causal structure discovery from road traffic data (First Job: Senior Research Engineer at NTU, Singapore)


• • Fei Wang, PhD student, on game theory for machine learning (First Job: Data Scientist at the CMCRC)


• • Goce Ristanoski, PhD student, on time series regression (First Job: Postdoc at CSIRO's Data61)


• • Mohammad Mazraehshahi, Master student, on soft-cut decision trees


• • DongHawn Lee, Master student, on lazy learning methods


• • Jinheng Liu, Master student, ensembles for outlier detection


• • Emma Wang, Master student, feature creation for Bagging


• • Chun Yuan Lee, Summer intern student, Causality Models for Understanding Road Traffic Changes


• • Amogh Sarda, Summer intern student, Incident impact analysis by earning historical road traffic data


• • Han Zhou, Summer intern student, Mining social networks for early detection of events


• • Zeyang Yu, Summer intern student, on Twitter-based road incident detection.


• • Mingxuan Li, Summer intern student (winner of NICTA summer scholar prize), on mining dynamic road traffics.

Wei's Academic Ancestry

我的学术祖普:

Source: www.genealogy.ams.org

•
• Jacob Bernoulli (伯努利家族)

↳
• Johann Bernoulli (约翰·伯努利)

↳
• Euler (欧拉)

↳
• Lagrange (拉格朗日)

↳
• Fourier (傅里叶)

↳
• Dirichlet (狄利克雷)

↳
• Lipschitz

↳
• Lindemann

↳
• Felix

↳
• Hilbert

↳
• Courant

↳
• Rellich

↳
• Cordes

↳
• Crandall

↳
• Evans

↳
• Lenhart

↳
• Chawla

↳
• Liu (刘伟)