Research Focus
  • Large-scale Graphic and Graph-embedding Models

Research in this area is primarily focused on large-scale algorithms and the innovative applications of graphical models and network-and-graph-based deep learning in financial scenarios. These applications include:

·       Handling recommendation, marketing, and risk control issues for trillion-dollar financial trading networks.

·       Managing corporate smart analysis and decision support engines based on enterprise knowledge maps.

·       Managing operational data and workflow.

·       Utilizing smart financial reasoning and the decision support engine based on financial knowledge maps.

  • Data Security and Privacy Protection With Machine Learning

This work is to combine privacy protection, information security and machine learning,  and study the distributed modeling and analysis on multi-party financial data without sharing, which can improve the utilization of multi-party financial data.

Products and Applications
  • Financial Brain

    Based on Ant Group's technological accumulation, the lab utilizes AI technologies to build up core financial AI capabilities, empowering Ant Group's internal applications such as smart marketing, smart security, smart financial information services, etc. Moreover, the lab supports partners and financial institutions in the ecosystem through platform products. is a smart information service system for corporate finance based on NLP processing technology. It collects 26 categories of enterprise intelligence information such as business dynamics, litigation cases, tax status, administrative penalties, investment and financing activities, changes of executives, and news events. The system uses AI technologies to clean, analyze, and associate non-structured text to form structured enterprise intelligence information. Since its launch in 2016, it has been widely used in corporate due diligence, risk management, compliance audits, industry research, and the screening of business and investment opportunities. Typical customers include Fortune 500 companies across industries such as banking, insurance, financial leasing, supply chain finance, private equity investment, and so on.

  • Smart Customer Service

    Ant Group officially launched Zero Cloud Customer Service. This new entity has served more than 3,000 financial institutions including securities, insurance, and banking companies. Ant Zero Cloud Customer Service is a comprehensive solution (deployment of private cloud products) combining AI, public cloud, and cloud customer service. It effectively resolves the problems of high cost and low efficiency associated with traditional customer service centers. Currently, it provides up to 85% self-service across different industrial applications and realizes 7x24 real-time responses to users’ questions by calls and text messages.

  • Smart Assistant

    Our smart assistant brings seamless human-machine interaction through voice, natural language, image recoginition and vision, emotion recognition, and human-machine dialogue technologies. It analyzes a user's information, problems, intentions, and emotions under different scenarios to accurately connects users with targeted services based on their needs. In this way, the smart assistant provides one-stop financial and livelihood services which are available to industry partners on the platform.



Academic Achievements
Publications and Presentations
  • Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, and Shu-Tao Xia. Iterative learning with open-set noisy labels. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
  • Bo Dai, Albert Shaw, Niao He, Lihong Li, and Le Song. Boosting the actor with dual critic. In International Conference on Learning Representations (ICLR), 2018
  • Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, and Le Song. Sbeed: Convergent reinforcement learning with nonlinear function approximation. International Conference on Machine Learning (ICML), 2018.
  • Hajun Dai, Zornitsa Kozareva, Bo Dai, Alex Smola, and Le Song. Learning steady states of iterative algorithms over graphs. ICML, 2018.
  • Weiyang Liu, Bo Dai, Xingguo Li, James Rehg, and Le Song. Towards black-box iterative machine teaching. ICML, 2018.
  • Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. Adversarial attack on graph structured data. ICML, 2018.
  • Jianfei Chen, Jun Zhu, and Le Song. Stochastic training of graph convolutional networks. ICML, 2018.
  • Jianbo Chen, Le Song, Martin Wainwright, and Michael Jordan. Learning to explain: An information-theoretic perspective on model interpretation. ICML, 2018.
  • Woosang Lim, Rundong Du, Bo Dai, Kyomin Jung, Le Song, and Haesun Park. Multi-scale nystrom method. Artificial Intelligence and Statistics (AISTATS), 2018.
  • Yichen Wang, Evangelos Theodorou, Apurv Verma, and Le Song. A stochastic differential equation framework for guiding online user activities in closed loop. AISTATS, 2018.
  • Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, and Le Song. Syntax-directed variational autoencoder for structured data. International Conference on Learning Representations (ICLR), 2018.
  • Weiyang Liu, Zhen Liu, Zhiding Yu, Bo Dai, Rongmei Lin, Yisen Wang, James Rehg, and Le Song. Decoupled networks. CVPR, 2018.
  • Y. Zhang, H. Dai, Z. Kozareva, A. Smola, and L. Song. Variational reasoning for question answering with knowledge graph. AAAI Conference on Artificial Intelligence (AAAI), 2018.
  • K. Kawaguchi, B. Xie, V. Vikas, and L. Song. Deep semi-random features for nonlinear function approximation. AAAI, 2018.
  • S. Xiao, M. Farajtabar, X. Ye, J. Yan, L. Song, and H. Zha. Learning conditional generative models for temporal point processes. AAAI, 2018.
  • Privacy Preserving Point-of-interest Recommendation Using Decentralized Matrix Factorization. Chaochao Chen, Ziqi Liu, Peilin Zhao, Jun Zhou, Xiaolong Li. AAAI, 2018.
  • Shaosheng Cao, Wei Lu, Jun Zhou and Xiaolong Li. cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information. AAAI, 2018.
  • Liu, Q., Xiang, B., Yuan, N. J., Chen, E., Xiong, H., Zheng, Y., & Yang, Y. (2017). An influence propagation view of PageRank. ACM, 11(3), 30.
  • Distributed Collaborative Hashing and Its Applications in Ant Financial. Chaochao Chen, Ziqi Liu, Peilin Zhao, Longfei Li, Jun Zhou, Xiaolong Li. KDD, 2018.
  • A Sparsity Guided Deep Framework for Cross-Domain and Cross-System Recommendations. Feng Zhu, Yan Wang, Chaochao Chen, Mehmet Orgun, Jia Wu, Guanfeng Liu. IJCAI, 2018.
  • Weiran Huang, Jungseul Ok, Liang Li, Wei Chen. Combinatorial Pure Exploration with Continuous and Separable Rewards and Its Applications. IJCAI, 2018.
  • Zhiqiang Zhang, Chaochao Chen, Jun Zhou and Xiaolong Li. An Industrial-scale System for Heterogeneous Information Card Ranking in Alipay. DASFAA, 2018.
  • Chuan Shi, Zhiqiang Zhang, Yugang Ji, Weipeng Wang, Philiph S. Yu and Zhiping Shi. SemRec: A Personalized Semantic Recommendation Method based on Weighted Heterogeneous Information Networks. WWW, 2018.
  • Ya-Lin Zhang, Longfei Li, Jun Zhou, Xiaolong Li, Zhi-Hua Zhou. Anomaly Detection with Partially Observed Anomalies. WWW, April 23-27, 2018, Lyon, France.
  • Wenjing Fang, Jun Zhou, Xiaolong Li, and Kenny Q. Unpack Local Model Interpretation for GBDT. ZhuDASFAA(International Conference on Database Systems for Advanced Applications.
  • Cen Chen, Yinfei Yang, Jun Zhou, Xiaolong Li and Forrest Sheng Bao. Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators. NAACL, 2018.
  • Yisen Wang, Bo Dai, Lingkai Kong, Sarah Monazam Erfani, James Bailey, Hongyuan Zha. Learning Deep Hidden Nonlinear Dynamics from Aggregate Data. UAI, 2018.
  • Ziqi Liu,Chaochao Chen, Xinxing Yang, Jun Zhou, Xiaolong Li, Le Song. Heterogeneous Graph Neural Networks for Malicious Account Detection. CIKM, 2018.
  • H. Dai, E. Khalil, Y. Zhang, B. Dilkina, and L.Song. Learning combinatorial optimization algorithms over graphs. Neural Information Processing Systems (NIPS), 2017.
  • S. Xiao, M. Farajtabar, X. Ye, J. Yan, L. Song, and H. Zha. Wasserstein learning of deep generative point process models. NIPS, 2017.
  • W. Liu, Y. Zhang, X. Li, Z. Yu, B. Dai, T. Zhao, and L. Song. Deep hyperspherical learning of convolution neural networks. NIPS, 2017.
  • L. Song, S. Vempala, J. Wilmes, and B. Xie. On the complexity of learning neural networks. NIPS, 2017.
  • Y. Wang, X. Ye, H. Zha, and L. Song. Predicting user activity level in point process models with mass transport equation. NIPS, 2017.
  • X. Xu, C. Liu, Q. Feng, H. Yin, L. Song, and D. Song. Neural network-based graph embedding for cross-platform binary code similarity detection. ACM Conference on Computer and Communications Security (CCS), 2017.
  • Kun He, Liang Li, Xingwu Liu, Yuyi Wang, Mingji Xia. Variable Version Lovász Local Lemma: Beyond Shearer’s Bound. FOCS, 2017.
  • Weiran Huang, Liang Li and Wei Chen. Partitioned Sampling of Public Opinions Based on Their Social Evolution. AAAI, 2017.
  • Ziqi Liu, Alex Smola, Kyle Soska, Yu-Xiang Wang, Qinghua Zheng, Jun Zhou. Attributing hacks with survival trend filtering. Electronic Journal of Statistics, 2017.
  • Wenpeng Zhang, Peilin Zhao, Wei Liu, Steven Hoi, Wenwu Zhu, Tong Zhang. Projection-Free Distributed Online Learning in Networks. ICML, 2017.
  • Jun Zhou, Xiaolong Li, Peilin Zhao, Chaochao Chen, Longfei Li, Xinxing Yang, Qing Cui, Jin Yu, Xu Chen, Yi Ding and Yuan Qi.KunPeng: Parameter Server based Distributed Learning Systems and Its Applications in Alibaba and Ant Financial. KDD, 2017.
  • Chenghao liu, Teng Zhang, Peilin Zhao, Jun Zhou, Jianling Sun. Locally Linear Factorization Machines. IJCAI, 2017.
  • Yong Liu, Peilin Zhao, Xin Liu, Min Wu, Lixin Duan, Xiaoli Li. Learning User Dependencies for Recommendation. IJCAI, 2017.
  • Shuji Hao, Peilin Zhao, Yong Liu, Steven Hoi, Chunyan Miao. Online Multitask Relative Similarity Learning. IJCAI, 2017.
  • Peng Yang, Peilin Zhao, Xin Gao. Robust Online Multi-Task Learning with Correlative and Personalized Structures. IEEE Transactions on Knowledge and Data Engineering (TKDE), June 2017.
  • Ziqi Liu, Alex Smola, Kyle Soska, Yu-Xiang Wang, Qinghua Zheng. Attributing Hacks. AISTATS, 2017.
  • Bo Dai, Albert Shaw, Lihong Li, Lin Xiao, Niao He, Zhen Liu, Jianshu Chen, and Le Song. Sbeed: Convergent reinforcement learning with nonlinear function approximation. International Conference on Machine Learning (ICML), 2018.

Scan QR code
关注Ali TechnologyWechat Account