I am currently an assistant professor at Department of Information Management and Business Intelligence, Fudan University. I obtained my Ph.D. degree from Zhejiang University in September 2021, co-advised by Yang Yang and Jiangang Lu. I have been visiting UCLA (working with Yizhou Sun) from Nov, 2019 to Apr, 2020.
My research interests include graph representation learning, social network analysis and data mining, including but not limited to: network denoising, robustness of machine learning models on graphs.
jiarongxu {at} fudan [dot] edu [dot] cn
Motivated students are welcome to contact for brainstorming!
Contact
We have open positions for postdoctoral. If interested,
lease read this for details and drop me your CV by email.
Contact
Network data in real-world tends to be error-prone due to incomplete sampling, imperfect measurements or even malicious attacks. This in turn results in inaccurate results when performing network analysis or modeling on these flawed networks.
Our research aims to reconstruct a reliable network from a flawed one, a process referred to network enhancement. More specifically, network enhancement aims to detect the noisy links that are observed in the network but should not exist in the real world, as well as to complement the missing links that do indeed exist in the real world yet remain unobserved.
From one perspective, we turns the network enhancement problem into edge sequences generation, and employ a deep reinforcement learning framework to solve it, which takes advantage of downstream task to guide the network denoising process (NetRL, Xu et al, TKDE'21).
From another perspective, we construct a self-supervised learning framework that identifies missing links and nosiy links simultaneously by leveraging the mutual influence of them (E-Net, Xu et al, TKDE'20).
Furthermore, we study the model robutness against adversarial attacks. Our work shows that even without any information about the target model, one can still perform effective attacks (Xu et al, AAAI'22). To handle the adversarial vulnerability problem, we further propose an unsupervised defense technique to robustify pre-trained deep graph models (Xu et al, AAAI'22).
We propose a general game bot detection framework for massively multiplayer online role playing games termed NGUARD+ (denoting NetEase Games’ Guard), which captures user patterns in order to identify game bots from player behavior sequences. NGUARD+ mainly employs attention-based methods to automatically differentiate game bots from humans. We provide a combination of supervised and unsupervised methods for game bot detection to detect game bots and new type of game bots even when the labels of game bots are limited ([Tao and Xu et al, KDD'18];[Xu et al, TKDD'20]).
2023
Jiarong Xu, Renhong Huang, Xin Jiang, Yuxuan Cao, Carl Yang, Chunping Wang, and Yang Yang.
Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks.
In Proceedings of the 37th Conference on Neural Information Processing System (NeurIPS’23).
[PDF] [Code]
Yuxuan Cao*, Jiarong Xu*#, Carl Yang, Jiaan Wang, Yunchao Mercer Zhang, Chunping Wang, Lei Chen, and Yang Yang.
When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'23).
[PDF] [Code]
(*: equal contribution, #: corresponding author)
Jiarong Xu, Yang Yang, Shiliang Pu, Yao Fu, Jun Feng, Weihao Jiang, Jiangang Lu and Cunping Wang.
NetRL: Task-aware Network Denoising via Deep Reinforcement Learning.
In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023. [PDF] [Code]
Haoyu Kuang, Jiarong Xu#, Haozhe Zhang, Zuyu Zhao, Qi Zhang, Xuanjing Huang, and Zhongyu Wei#.
Unleashing the Power of Language Models in Text-Attributed Graph.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP’23 Findings).
(#: corresponding author)
Ruoxue Ma, Jiarong Xu#, Xinnong Zhang, Haozhe Zhang, Zuyu Zhao, Qi Zhang, Xuanjing Huang, and Zhongyu Wei#.
One-Model-Connects-All: A Unified Graph Pre-Training Model for Online Community Modeling.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP’23 Findings).
(#: corresponding author)
Taoran Fang, Zhiqing Xiao, Chunping Wang, Jiarong Xu, Xuan Yang, and Yang Yang.
DropMessage: Unifying Random Dropping for Graph Neural Networks.
In Proceedings of the 37th Conference on Artificial Intelligence (AAAI'23).
[PDF]
(Distinguished Paper Award)
Xinke Jiang, Zidi Qin, Jiarong Xu, and Xiang Ao.
Incomplete Graph Learning via Attribute-Structure Decoupled Variational Auto-Encoder.
In Proceedings of the 17th ACM International Conference on Web Search and Data Mining (WSDM'23).
Siyuan Wang, Zhongyu Wei, Jiarong Xu, Taishan Li, and Zhihao Fan.
Unifying Structure Reasoning and Language Pre-training for Complex Reasoning Tasks.
In IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2023.
[PDF]
Jiaan Wang, Fandong Meng, Yunlong Liang, Tingyi Zhang, Jiarong Xu, Zhixu Li, Jie Zhou.
Understanding Translationese in Cross-Lingual Summarization.
In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP’23 Findings).
2022
Jiarong Xu, Yang Yang, Junru Chen, Xin Jiang, Chunping Wang, Jiangang Lu and Yizhou Sun.
Unsupervised Adversarially Robust Representation Learning on Graphs.
In Proceedings of the 36th Conference on Artificial Intelligence (AAAI’22). [PDF] [Code]
Jiarong Xu, Yizhou Sun, Xin Jiang, Yanhao Wang, Chunping Wang, Jiangang Lu and Yang Yang.
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs.
In Proceedings of the 36th Conference on Artificial Intelligence (AAAI’22). [PDF] [Code]
Jiarong Xu, Yang Yang, Chunping Wang, Zongtao Liu, Jing Zhang, Lei Chen and Jiangang Lu.
Robust Network Enhancement from Flawed Networks.
In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022. [PDF] [Code]
Xuanwen Huang, Yang Yang, Yang Wang, Chunping Wang, Zhisheng Zhang, Jiarong Xu, and Lei Chen.
DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection.
In Proceedings of the 36th Conference on Neural Information Processing System Track on Datasets and Benchmarks (NeurIPS’22 D&B).
[PDF]
[DGraph Data]
Ziwei Chai, Siqi You, Yang Yang, Shiliang Pu, Jiarong Xu, Haoyang Cai, and Weihao Jiang.
Can Abnormality be Detected by Graph Neural Networks?
In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI'22).
[PDF] [Code]
Yifei Sun, Haoran Deng, Yang Yang, Chunping Wang, Jiarong Xu, Renhong Huang, Linfeng Cao, Yang Wang and Lei Chen.
Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network.
In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI'22).
[PDF] [Code]
2021 and prior
Jiarong Xu, Yifan Luo, Jianrong Tao, Changjie Fan, Zhou Zhao and Jiangang Lu.
NGUARD+: A Attention-based Game Bot Detection Framework via Player Behavior Sequences.
In ACM Transactions on Knowledge Discovery from Data (TKDD), 2020. [PDF]
Jianrong Tao*, Jiarong Xu*, Linxia Gong, Yifu Li, Changjie Fan and Zhou Zhao.
NGUARD: A Game Bot Detection Framework for NetEase MMORPGs.
In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'18).
[PDF] (*: equal contribution)
Qinkai Zheng, Xu Zou, Yuxiao Dong, Yukuo Cen, Da Yin, Jiarong Xu, Yang Yang, and Jie Tang.
Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning.
In Proceedings of the 35th Conference on Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS’21 D&B). [PDF] [Code]
Yiren Shen, Xiaoxian Ou, Jiarong Xu, Guanglin Zhang, Lin Wang and Dapeng Li.
Optimal energy storage management for microgrids with ON/OFF co-generator: A two-time-scale approach.
In Proceedings of the 3rd IEEE Conference on Signal and Information Processing (GlobalSIP'15).
[PDF]
Chen Chen, Xueyuan Li, Ye Yang, Jiarong Xu, Zuwei Liao, Xinggao Liu and Jinshui Chen and Jiangang Lu.
Parameter Self-Tuning of SISO Compact-Form Model-Free Adaptive Controller based on Neural Network with System Error Set as Input.
In Proceedings of the 12th Asian Control Conference (ASCC'19).
[PDF]
Ye Yang, Jinhou Han, Chen Chen, Jiarong Xu, Zuwei Liao, Xinggao Liu, Jinshui Chen and Jiangang Lu.
A PSO-LP Cooperative Algorithm for Mixed Integer Nonlinear Programming.
In Proceedings of the 12th Asian Control Conference (ASCC'19).
[PDF]
PC Members: KDD, NeurIPS, ICLR, WWW, AAAI, WSDM, EMNLP, ECML-PKDD, SDM
Reviewers: IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transaction on Big Data, IEEE Transactions on Network and Service Management
Guest Editor of IEEE Transactions on Big Data (TBD)