人员简介

张亮

职务/职称

研究科学家

研究方向

强化学习、智能楼宇,博弈论与网络优化

电子邮箱

zhangliangshuxue@gmail.com

教育背景

华中科技大学,学士, 2011

香港理工大学, 博士, 2016

主要成果/荣誉

国际会议Buildsys 2014的最佳论文奖

深圳市海外高层次人才(C类)

个人介绍

2017-2022年先后入职京东和腾讯,发表在KDD、SIGIR等多项强化学习决策研究成果在京东商业广告和腾讯王者荣耀上线应用,谷歌引用量1100+。后加入鹏城实验室,担任副研究员。主要研究方向: 强化学习,智能楼宇,博弈论与网络优化等。

代表性论文

博弈论与网络优化

1,Y. Zhao, H. Wang, H. Su, L. Zhang, R. Zhang, D. Wang, K. Xu,“Understand love of variety in wireless data market under sponsored data plans”,IEEE JSAC 2020  (CCF-A)

2,Y. Zhao, H, Su, L. Zhang, D. Wang, K. Xu, "Variety Matters: A New Model for the Wireless Data Market under Sponsored Data Plans", in Proc. of IEEE/ACM IWQoS 2019. (CCF-B)

3, Liang Zhang, Weijie Wu and Dan Wang, "TDS: Time-Dependent Sponsored Data Plan for Wireless Data Traffic Market", in Proc. of IEEE INFOCOM 2016. (CCF-A)

4, Liang Zhang, Weijie Wu and Dan Wang,"Sponsored Data Plan: A Two-Class Service Model in Wireless Data Networks", in Proc. of ACM SIGMETRICS 2015. (CCF-B, CORE* A)

5, Liang Zhang, Weijie Wu and Dan Wang, "Time Dependent Pricing in Wireless Data Networks: Flat-rates vs. Usage-based Schemes", in Proc. of IEEE INFOCOM, 2014  (CCF-A)

绿色智能楼宇

6, Z Zheng, F Wang, D Wang, L Zhang, "An Urban Mobility Model with Buildings Involved: 

Bridging Theory to Practice", ACM TOSN 2020 (CCF-B)

7,Z. Zheng, F. Wang, D. Wang, and L. Zhang, "Buildings affect Mobile Pattens: Developing a new Urban Mobility Model", in Proc. of ACM Buildsys’18 (Best Paper Award)

8,L. Zhang, A. H. Lam and D. Wang, "Strategy proof Thermal Comfort Voting in Buildings,

 in Proc. of ACM BuildSys’14

强化学习以及应用

9, D. Zhao, L. Zhang*, B. Zhang, L. Zheng, Y. Bao, W. Yan, "MaHRL: Multi-goals Abstraction based Deep Hierarchical Reinforcement Learning for Recommendations", in Proc. of ACM SIGIR 2020 (CCF-A)

10, Y. Su, L. Zhang*, Q. Dai, B. Zhang, J. Yan, S. Xu, D. Wang, Y. He,  Y. Bao, and W. Yan, "An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration", in Proc. of IJCAI 2020 (CCF-A)

11, Y. Wang, L. Zhang(co-first author), Q. Dai, F. Sun, B. Zhang, Y. He, Y. Bao and W. Yan , "Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction", in Proc. of ACM CIKM 2019  (CCF-B)

12, X. Zhao, L. Xia, L. Zhang, Z. Ding, D. Yin, J. Tang, "Deep Reinforcement Learning for Page-wise Recommendations", in Proc. of ACM RecSys 2018 (CCF-B,高引论文270+)

13, X. Zhao, L. Zhang, Z. Ding, L. Xia, J. Tang, and D. Yin. "Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning". in Proc. of ACM SIGKDD 2018. (CCF-A,高引论文280+)

14,W. Lu, F. Chung, K. Lai, L. Zhang,"Recommender system based on scarce information  mining", Neural Networks, 2017 (CCF-B)

15, Q Dai, X Shen, Z Zheng, L Zhang, Q Li, D Wang, "Adversarial training regularization for negative sampling based network embedding", Information Sciences 2021 (CCF-B)

16, Q. Dai, X. Shen, L. Zhang, Q. Li, D. Wang, "Adversarial Training Methods for Network Embedding", in Proc. of ACM WWW 2019 (CCF-A)