Ordered by topics (* indicates equal contribution or corresponding author)                                        

Responsible Generative AI and Foundation Models:

• Pushing the Limits of ChatGPT on NLP Tasks.

Xiaofei Sun, Linfeng Dong, Xiaoya Li, Zhen Wan, Shuhe Wang, Tianwei Zhang, Jiwei Li, Fei Cheng, Lingjuan Lyu, Fei Wu, Guoyin Wang.

• [ICLR’24 Oral (top 1.2%)] Detecting, Explaining, and Mitigating Memorization in Diffusion Models. 

Yuxin Wen, Yuchen Liu, Chen Chen, Lingjuan Lyu*.

• [ICLR’24] DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models. 

Zhenting Wang, Chen Chen, Lingjuan Lyu*, Dimitris N. Metaxas, Shiqing Ma.

• [Nature Machine Intelligence’23] (IF: 25.898) Defending ChatGPT against Jailbreak Attack via Self-Reminder.

Fangzhao Wu, Yueqi Xie, Jingwei Yi, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie.

• When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions.

Weiming Zhuang, Chen Chen, Lingjuan Lyu.

• [NeurIPS’23] Where Did I Come From? Origin Attribution of AI-Generated Images.

Zhenting Wang, Chen Chen, Yi Zeng, Lingjuan Lyu*, Shiqing Ma.

• [IJCAI’23, Early Career Spotlight] A Pathway Towards Responsible AI Generated Content. Blog.

Chen Chen, Jie Fu, Lingjuan Lyu*.

• [Area Chair Award, ACL’23] Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark. 

Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Benjamin Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun and Xing Xie.

• [NeurIPS 2022] CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks. (Code, blog) 

Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu*, Fangzhao Wu, Jiwei Li, Ruoxi Jia.

• [EMNLP’22 Oral] Extracted BERT Model Leaks More Information than You Think! 

Xuanli He, Chen Chen, Lingjuan Lyu* and Qiongkai Xu.

• [COLING’22 Long] Beyond Model Extraction: Imitation Attack for Black-Box NLP APIs.

Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari.     

• [AAAI 2022 Oral] Protecting Intellectual Property of Language Generation APIs with Lexical Watermark. Code.

Xuanli He, Qiongkai Xu, Lingjuan Lyu*, Fangzhao Wu, Chenguang Wang. 

• [NAACL’21 Main Paper] Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! (Blog. Code)

Xuanli He, Lingjuan Lyu*, Qiongkai Xu, Lichao Sun. 

Federated Learning: 

• [CVPR’24] FedMef: Towards Memory-efficient Federated Dynamic Pruning.

Hong Huang, Weiming Zhuang, Chen Chen, Lingjuan Lyu*

• [ICLR’24] FedWon: Triumphing Multi-domain Federated Learning Without Normalization. 

Weiming Zhuang, Lingjuan Lyu*.

• [ICLR’24] FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity.

Kai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu*.

• [NeurIPS’23] Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning. 

Yue Tan, Chen Chen, Weiming Zhuang, Xin Dong, Lingjuan Lyu*, Guodong Long.

• [NeurIPS’23] Towards Personalized Federated Learning via Heterogeneous Model Reassembly. 

Jiaqi Wang, Xingyi Yang, Suhan Cui, Liwei Che, Lingjuan Lyu, Dongkuan Xu, Fenglong Ma.

• [KDD'23 FL4Data-Mining workshop, Best Industry Paper Award] Is Normalization Indispensable for Multi-domain Federated Learning.

Weiming Zhuang, Lingjuan Lyu*.

• [ICCV’23] TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation.

Jie Zhang, Chen Chen, Weiming Zhuang, Lingjuan Lyu*.

• [ICCV’23] MAS: Towards Resource-Efficient Federated Multiple-Task Learning.

Weiming Zhuang, Yonggang Wen, Lingjuan Lyu, Shuai Zhang..

• [TDSC’23] FederBoost: Private Federated Learning for GBDT.

Tian, Zhihua; Zhang, Rui; Hou, Xiaoyang; Lyu, Lingjuan; Zhang, Tianyi; Liu, Jian; Ren, Kui..

• [ICML’23] Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting.

Yuchen Liu, Chen Chen, Lingjuan Lyu*, Fangzhao Wu, Sai Wu, Gang Chen.

• [IJCAI’23] FedSampling: A Better Sampling Strategy for Federated Learning.

Tao Qi, Fangzhao Wu, Lingjuan Lyu, Yongfeng Huang, Xing Xie.

• ​​[IJCAI’23] Reducing Communication for Split Learning by Randomized Top-k Sparsification.

Fei Zheng, Chaochao Chen, Lingjuan Lyu, Binhui Yao.

• [ICLR’23 Oral, notable top 1.5%] MocoSFL: enabling cross-client collaborative self-supervised learning.  Code.

Jingtao Li, Lingjuan Lyu*, Daisuke Iso, Chaitali Chakrabarti, Michael Spranger.

• [AAAI’23] Delving into the Adversarial Robustness of Federated Learning. 

Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu*, Shuang Wu, Shouhong Ding, Chao Wu.

• [NeurIPS 2022] Calibrated Federated Adversarial Training with Label Skewness. 

Chen Chen, Yuchen Liu, Xingjun Ma, Lingjuan Lyu*.

• [NeurIPS 2022] DENSE: Data-Free One-Shot Federated Learning.

Jie Zhang#, Chen Chen#, Bo Li, Lingjuan Lyu*, Shuang Wu, Shouhong Ding, Chunhua Shen, Chao Wu.

• [NeurIPS 2022] FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning. 

Tao Qi, Fangzhao Wu, Chuhan Wu, Lingjuan Lyu, Tong Xu, Hao Liao, Zhongliang Yang, Yongfeng Huang, Xing Xie.

• [CIKM’22 FedGraph Best Paper Award]. VFGNN: A Mixed Framework for Vertically Federated Graph Neural Network.

Chaochao Chen, Fei Zheng, Jun Zhou, Lingjuan Lyu, Longfei Zheng, Li Wang and Xiaolin Zheng.

• [Nature Communications’22] A Federated Graph Neural Network Framework for Privacy-Preserving Personalization. (IF: 14.919)  

Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, Tao Qi, Yongfeng Huang, and Xing Xie.  

• [Nature Communications’22] Communication-Efficient Federated Learning via Knowledge Distillation. (IF: 14.919)          

Yongfeng Huang, Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, and Xing Xie.

• [TNNLS’22] (IF: 10.451) Privacy and Robustness in Federated Learning: Attacks and Defenses. 

Lingjuan Lyu, Han Yu, Xingjun Ma, Chen Chen, Lichao Sun, Jun Zhao, Qiang Yang, Philip S. Yu.

• [ICDM’22 Long, acceptance rate: 9.77%] FedSkip: Combatting Statistical Heterogeneity with Federated Skip Aggregation. 

Ziqing Fan, Yanfeng Wang, Jiangchao Yao, Lingjuan Lyu, Ya Zhang, and Tian Qi.

• [ICML’22  Spotlight] Accelerated Federated Learning with Decoupled Adaptive Optimization.

Jiayin Jin, Jiaxiang Ren, Yang Zhou, Lingjuan Lyu, Ji Liu, Dejing Dou.        

• [KDD’22] No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices.  

Ruixuan Liu, Fangzhao Wu, Chuhan Wu, Yanlin Wang, Lingjuan Lyu, Hong Chen, Xing Xie. 

• [IJCAI‘22 long, acceptance rate: 3.75%] Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification.

Chaochao Chen, Longfei Zheng, Huiwen Wu, Lingjuan Lyu, Jun Zhou, Jia Wu, Bingzhe Wu, Ziqi Liu, Li Wang, Xiaolin Zheng. 

• [TBD’22] Practical Attribute Reconstruction Attack Against Federated Learning. (IF: 3.344)

Chen Chen, Lingjuan Lyu*, Han Yu, Gang Chen. 

• [FL-AAAI’22 Oral, Best Student Paper Award] GEAR: A Margin-based Federated Adversarial Training Approach. 

Chen Chen, Jie Zhang and Lingjuan Lyu*. 

• [FL-AAAI’22 Oral] Byzantine-resilient Federated Learning via Gradient Memorization.   

Chen Chen, Lingjuan Lyu*, Yuchen Liu, Fangzhao Wu, Chaochao Chen and Gang Chen. 

• [NeurIPS 2021] Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation.

Jamie Cui, Chaochao Chen, Lingjuan Lyu, Carl Yang, Wang Li.

• [FTL-IJCAI’21 Oral] A Novel Attribute Reconstruction Attack in Federated Learning.

Lingjuan Lyu, Chen Chen. 

• [FL-ICML'21 Oral] FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation.

Chuhan Wu, Fangzhao Wu, Yang Cao, Lingjuan Lyu, Yongfeng Huang and Xing Xie. 

• [FL-ICML'21 Oral] A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning. 

Xinyi Xu, Lingjuan Lyu*. 

• [IJCAI’21, Most Influential IJCAI Papers (2022-02)] Federated model distillation with noise-free differential privacy. 

Lichao Sun, Lingjuan Lyu*. 

• [TIST’21] FedBERT: When Federated Learning Meets Pre-Training. (IF: 4.654)

Yuanyishu Tian, Yao Wan, Lingjuan Lyu, Dezhong Yao, Hai Jin, Lichao Sun. 

• [JIOT'21] Data Poisoning Attacks on Federated Machine Learning. (IF: 9.471, JCR:Q1)

Gan Sun, Yang Cong, Jiahua Dong, Qiang Wang, Lingjuan Lyu and Ji Liu. 

• [TIST’21] FedCTR: Federated Native Ad CTR Prediction with Cross Platform User Behavior Data. (IF: 4.654)

Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, Yongfeng Huang, and Xing Xie. 

• [FL-IJCAI’20] Threats to Federated Learning: A Survey. 

Lingjuan Lyu, Han Yu, Qiang Yang. 

Privacy:

• [NeurIPS’23] Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

Xiaoxiao Sun, Nidham Gazagnadou, Vivek Sharma, Lingjuan Lyu*, Hongdong Li, Liang Zheng. 

• [NeurIPS’23] UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition.

Yuyuan Li, Chaochao Chen, Yizhao Zhang, Weiming Liu, Lingjuan Lyu, Xiaolin Zheng, Dan Meng, Jun Wang. 

• [ICML’23] Fast Federated Machine Unlearning with Nonlinear Functional Theory.

Tianshi Che, Yang Zhou, Zijie Zhang, Lingjuan Lyu, Ji Liu, Da Yan, Dejing Dou, Jun Huan. 

• [NeurIPS 2022] Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling. CN Patent.

Junyuan Hong, Lingjuan Lyu*, Jiayu Zhou, Michael Spranger.

• [NeurIPS 2022] Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization. 

Zijie Zhang, Xin Zhao, Tianshi Che, Yang Zhou*, Lingjuan Lyu*.

• [CIKM’22, Best Paper Runner-up Award, only 1] Cross-Network Social User Embedding with Hybrid Differential Privacy Guarantees.

Jiaqian Ren, Lei Jiang, Hao Peng, Lingjuan Lyu, Zhiwei Liu, Chaochao Chen, Jia Wu, Xu Bai and Philip Yu.

• [ICML’22 long, Outstanding Paper Award] Privacy for Free: How does Dataset Condensation Help Privacy?; CN & US Patents; Top 17 ‘Must-Read’ AI Papers in 2022; Top 10 Machine Learning Papers of 2022 (1, 2); 

Tian Dong, Bo Zhao, Lingjuan Lyu*. 

• [WWW’22] Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation.

Chaochao Chen, Huiwen Wu, Jiajie Su, Lingjuan Lyu, Xiaolin Zheng and Li Wang.

• [EMNLP'20] Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness. (Code)

Lingjuan Lyu, Xuanli He, and Yitong Li. 

• [SIGIR'20] Towards Differentially Private Text Representations. (code, blog)

Lingjuan Lyu, Yitong Li, Xuanli He, Tong Xiao. 

• [SIGIR'20] Differentially Private Knowledge Distillation for Mobile Analytics 

Lingjuan Lyu, Chi-Hua Chen. 

• [JIOT’20] Local differential privacy based federated learning for Internet of Things. (IF: 9.515, JCR:Q1)

Yang Zhao, Jun Zhao, Mengmeng Yang, Teng Wang, Ning Wang, Lingjuan Lyu, Dusit Niyato, Kwok Yan Lam. 

• [JIOT’20] Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices. (IF: 9.515, JCR:Q1)

Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Zengxiang Li, Lingjuan Lyu, and Yingbo Liu.

• [TCC’20] Cloud-based Privacy-Preserving Collaborative Consumption in Sharing Economy. (IF: 5.720, SJR:Q1. Code)

Lingjuan Lyu, Sid Chi-Kin Chau, Nan Wang and Yifeng Zheng. 

• [JSAC’20] FORESEEN: Towards Differentially Private Deep Inference for Intelligent Internet of Things. (IF: 9.302, SJR:Q1, CCF: A)

Lingjuan Lyu, James C. Bezdek, Jiong Jin, and Yang Yang. 

• [TII’18] PPFA: Privacy Preserving Fog-enabled Aggregation in Smart Grid. (IF: 9.112, JCR:Q1. Code).  

L. Lyu, K. Nandakumar, B. Rubinstein, J. Jin, J. Bedo, and M. Palaniswami. 

• [CIKM'17] Privacy-Preserving collaborative deep learning with application to human activity recognition. (Code)

Lingjuan Lyu, Xuanli He, Yee Wei Law, Marimuthu Palaniswami. 

Model Robustness & Security (Backdoors/Poisoning attack&defense, adversarial attack&defense, robustness to domain drift, etc):

• [Best Student Paper Award, FL-IJCAI’23] Exploit Gradient Skew to Circumvent Byzantine Defenses for Federated Learning.

• [ICCV’23] The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning.

YVirat Shejwalkar, Lingjuan Lyu*, Amir Houmansadr.

• [CCS’23] NARCISSUS: A Practical Clean-Label Backdoor Attack with Limited Information.

Yi Zeng, Minzhou Pan, Hoang Anh Just, Lingjuan Lyu*, Meikang Qiu, Ruoxi Jia..

• [ICML’23] Reconstructive Neuron Pruning for Backdoor Defense.

Yige Li, Xixiang Lyu, Xingjun Ma, Nodens Koren, Lingjuan Lyu, Bo Li, Yu-Gang Jiang.

• [ICML’23] Revisiting Data-Free Knowledge Distillation with Poisoned Teachers.

Junyuan Hong, Yi Zeng, Shuyang Yu, Lingjuan Lyu*, Ruoxi Jia, Jiayu Zhou. 

• [ICML’23] Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing.

Jiaxiang Ren, Jiayin Jin, Yang Zhou, Lingjuan Lyu*, Da Yan.

• [IJCAI’23] RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation.

Qucheng Peng, Zhengming Ding, Lingjuan Lyu, Lichao Sun, Chen Chen. 

• [ICLR’23] MECTA: Memory-Economic Continual Test-Time Model Adaptation. Code.

Junyuan Hong, Lingjuan Lyu*, Jiayu Zhou, Michael Spranger. 

• [ICLR’23] Twofer: Tackling Continual Domain Shift with Simultaneous Domain Generalization and Adaptation. Code.

Chenxi Liu, Lixu Wang, Lingjuan Lyu*, Chen Sun, Xiao Wang, Qi Zhu. 

• [ICASSP’23] Towards Adversarially Robust Continual Learning.

Tao Bai, Chen Chen, Lingjuan Lyu*, Jun Zhao, Bihan Wen. 

• [ICLR’23] Towards Robustness Certification Against Universal Perturbations.

Yi Zeng, Zhouxing Shi, Ming Jin, Feiyang Kang, Lingjuan Lyu*, Cho-Jui Hsieh, Ruoxi Jia. 

• [ICLR’23] IDEAL: Query-Efficient Data-Free Learning from Black-Box Models. Code.

Jie Zhang, Chen Chen, Lingjuan Lyu*. 

• [Usenix’23] How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?

Yi Zeng, Minzhou Pan, Himanshu Jahagirdar, Ming Jin, Lingjuan Lyu, Ruoxi Jia.

• [WWW’23] Minimum Topology Attacks for Graph Neural Networks. 

Mengmei Zhang, Xiao Wang, Chuan Shi, Lingjuan Lyu, Tianchi Yang and Junping Du.

• [AAAI’23] Defending Against Backdoor Attacks in Natural Language Generation. 

Xiaofei Sun, Xiaoya Li, Yuxian Meng, Xiang Ao, Lingjuan Lyu, Jiwei Li, Tianwei Zhang.

• [EMNLP’22] Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models. CN Patent.

Zhiyuan Zhang, Lingjuan Lyu*, Xingjun Ma, Chenguang Wang and Xu Sun.

• [ICLR’22] How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data. CN Patent.

Zhiyuan Zhang, Lingjuan Lyu*, Weiqiang Wang, Lichao Sun, Xu Sun.            

• [NeurIPS 2021] Anti-Backdoor Learning: Training Clean Models on Poisoned Data. (Code)

Yige Li, Xixiang Lyu, Xingjun Ma, Nodens Koren, Lingjuan Lyu, Bo Li.

• [ICLR'21] Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks. (Code)

Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma. 

• [TDSC’22] Decision Boundary-aware Data Augmentation for Adversarial Training. (IF: 7.329)

Chen Chen, Jingfeng Zhang, Xilie Xu, Lingjuan Lyu*, Chaochao Chen, Tianlei Hu, and Gang Chen.

• [FGCS'20] A Fast and Scalable Authentication Scheme in IoT for Smart Living. (IF: 6.125, SJR:Q1)

Jianhua Li*, Jiong Jin, Lingjuan Lyu*, Dong Yuan, Yingying Yang, Longxiang Gao, Chao Shen. 

Fairness/incentive FL:

• [NeurIPS 2021] Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning. (Code)

Xu Xinyi, Lingjuan Lyu*, Xingjun Ma, Chenglin Miao, Chuan-Sheng Foo, Bryan Kian Hsiang Low.

• [FL-IJCAI’20, Best Paper Award] Collaborative Fairness in Federated Learning. 

Lingjuan Lyu, Xinyi Xu and Qian Wang. 

•  [TDSC’20] How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning. (IF: 6.404, SJR:Q1, CCF: A, Core ranking: A)

Lingjuan Lyu, Yitong Li, Karthik Nandakumar, Jiangshan Yu, Xingjun Ma. 

• [TPDS’20] Towards Fair and Privacy-Preserving Federated Deep Models. (IF: 3.402, SJR:Q1, CCF: A, Core ranking: A*. Code, blog, youtube, zhihu) Most popular award, NTU College of Engineering Video Competition.

Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin, Han Yu, and Kee Siong Ng. 

Other topics (Distillation, CV, Graph, IoT, etc):

• [TNNLS’23] (IF: 10.451) InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation. 

Jiahua Dong, Yang Cong, Gan Sun, Lixu Wang, Lingjuan Lyu, Jun Li, and Ender Konukoglu.

• [IJCAI‘22] Data-Free Adversarial Knowledge Distillation for Graph Neural Networks.

Yuanxin Zhuang, Lingjuan Lyu, Chuan Shi, Carl Yang, Lichao Sun. 

• [KDD’22] EdgeWatch: Collaborative Investigation of Data Integrity at the Edge based on Blockchain.  

Bo Li, Qiang He, Feifei Chen, Lingjuan Lyu, Athman Bouguettaya, Yun Yang.

• [AAAI’22 AI for Transportation Workshop, Best Paper Award] DADFNet: Dual Attention and Dual Frequency-Guided Dehazing Network for Video-Empowered Intelligent Transportation.      

Yu Guo, Wen Liu, Jiangtian Nie, Lingjuan Lyu, Zehui Xiong, Jiawen Kang, Han Yu and Dusit Niyato. 

• [TKDE'22] Traffic Anomaly Prediction Based on Joint Static-Dynamic  Spatio-Temporal Evolutionary Learning. (IF: 6.093)

Xiaoming Liu, Zhanwei Zhang, Lingjuan Lyu, Zhaohan Zhang, Shuai Xiao, Chao Shen, Philip Yu. 

• [TNNLS'21] Joint Stance and Rumour Detection in Hierarchical Heterogeneous Graph. (IF: 8.793, JCR:Q1)

Li, Chen; Peng, Hao; Li, Jianxin; Sun, Lichao; Lyu, Lingjuan; Wang, Lihong; Yu, Philip; He, Lifang

• [TII’19] Fog-embedded Deep Learning for the Internet of Things. (IF: 9.112, JCR:Q1). 

Lingjuan Lyu, James C Bezdek, Xuanli He, and Jiong Jin. 

• [JIOT’17] Fog-Empowered Anomaly Detection in Internet of Things using Hyperellipsoidal Clustering. (IF: 9.515, JCR:Q1. Code).    

Lingjuan Lyu, Jiong Jin, Sutharshan Rajasegarar, Xuanli He, Marimuthu Palaniswami.

Book chapters & Tutorials

• Threats to Federated Learning. Book “Federated Learning: Privacy and Incentive”. Springer Nature.

•  Collaborative Fairness in Federated Learning. Book “Federated Learning: Privacy and Incentive”. Springer Nature.

•  [WWW’22 Tutorials] Trustworthy AI: A Computational Perspective. 

Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Jamell Dacon, Lingjuan Lyu and Jiliang Tang.