Bing Luo (罗冰)

Bing Luo Assistant Professor of Data and Computational Science, Duke Kunshan University Email: bing.luo [at] dukekunshan.edu.cn Research Interests: Federated learning and analytics, edge computing and IoT, optimization and game theory, 5G/6G wireless communications and energy harvesting systems

Recruiting

Biography

I was a visiting scholar at Yale University, hosted by Prof. Leandros Tassiulas, Friedrich-Alexander-University Erlangen-Nuremberg, hosted by Prof. Robert Schober, Aalto University, hosted by Prof. Jyri Hämäläinen, and IBM T. J. Watson Research Center, hosted by Dr. Shiqiang Wang. Before pursuing my Ph.D. degree, I was a project manager at the Department of Networking, China Mobile Corporation, Beijing, China

News

[Aug. 2023] My Federated Learning research proposal (PI) received funding from the 2023 Suzhou Basic Research Program (Frontier Technology Research). This project is in collaboration with China Mobile (Suzhou) R&D Center and Soochow University.

[Jun. 2023]] Our paper on differential private federated analytics has been accepted by Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities (FL-ICML' 23). Congratulations to my supervised CUHKSZ undergraduate student Jiaqi Shao, who will become a PhD student at HKUST this Fall co-supervised by me and Prof. Xuanyu Cao!

[May. 2023] Our paper on federated reinforcement learning for robotics has been accepted by ICDCS 2023 Demo and Poster program. Congratulations to my supervised CUHKSZ undergraduate students Wenli Xiao (admitted by CMU Robotics Institute) and Tingwei Ye(now in NYU)!

[Apr. 2023] Our paper on incentivizing unbiased federated learning has been accepted to ICDCS 2023 (Track on AI for Distributed Systems and Distributed Systems for AI）

[Mar. 2023] Our paper "Optimization Design for Federated Learning in Heterogeneous 6G Networks" got accepted in IEEE Network, Special Issue on 6G Network AI Architecture for Customized Services and Applications, 2023.

[Jan. 2023] I was elected as the Executive Committee at the Technical Committee of Computational Economics (TCCE), China Computer Federation (CCF)

[Sep. 2022] I joined Duke Kunshan University (DKU) as a Tenure-Track Assistant Professor.

[June, 2022] Prof. Jianwei Huang and I have organized a series of federated learning online seminars at AIRS in this June. The invited speakers and talk details are as follows:

• Session 1 (7th June): Prof. Salman Avestimehr (USC), Dr. Chaoyang He (FedML), video online available.

• Session 2 (14th June): Prof. Leandros Tassiulas (Yale), Prof. Qiang Yang (WeBank & HKUST), vedio online available.

• Session 3 (21th June): Dr. Bing Luo (AIRS & Yale), Dr. Shiqiang Wang (IBM), vedio online available.

• Session 4 (28th June): Dr. Peter Kairouz (Google), Prof. Bo Li (UIUC), vedio online available.

Research Highlights

Optimization and System Development for Federated Learning in Mobile and IoT Networks This is a collaborative research project with Prof. Jianwei Huang, Prof. Leandros Tassiulas, and Dr. Shiqiang Wang (IBM T. J. Watson Research Center). I lead a small team of graduate (Xiang Li) and undergraduate (Wenli Xiao, Jiaqi Shao, Yingyi Huang, and Yutong Feng) students from CUHKSZ in developing edge-based cross-device federated learning prototypes. Check out our Fed-Mobile and Fed-IoT prototypes on the left side. Our prototype supports Mobile and IoT devices operating at WiFi and USRP-based 4G/5G wireless networks.

I. Adaptive Client Sampling for Federated Learning This sub-project aims to design optimal client sampling probability to tackle system heterogeneity (e.g., computation and communication capabilities) and statistical heterogeneity (non-i.i.d. and unbalanced data) for fast convergence with respect to wall-clock time. Our paper “Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling” published in IEEE INFOCOM, 2022

II. Cost-Effective Federated Learning Design This sub-project aims to minimize the total FL resource cost via optimizing the key control parameters of number of local iteration steps and number of per-round participants. Our paper “Cost-Effective Federated Learning Design” published in IEEE INFOCOM, 2021. Our paper “Cost-Effective Federated Learning in Mobie Edge Networks” published in IEEE JSAC Special Issue on Distributed Learning over Wireless Edge Networks, 2021.

Game-Theoretic Incentive Mechanism for Unbiased Federated Learning Motivation: Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server. However, due to system heterogeneity and limited budget, it is generally impractical for the server to incentivize all clients to participate in all training rounds (known as full participation). Approach: This project aims to propose a game-theoretic incentive mechanism for FL with randomized client participation, where the server adopts a customized pricing strategy that motivates different clients to join with different participation levels (probabilities) for obtaining an unbiased and high-performance model. Our paper “"Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation" got accepted in IEEE ICDCS 2023.

Federated Reinforcement Learning for Robotics Our paper "FedRos - Federated Reinforcement Learning for Networked Mobile-Robot Collaboration" has been accepted by ICDCS 2023 Demo and Poster program. My research project “Federated Learning for Multi-Robotics Cooperation” got funded with 500,000rmb from AIRS! (July. 2021-June. 2022). I lead this project with two excellent research interns Wenli Xiao and Tingwei Ye from CUHK(SZ). Check out our developed demo and cool NAO robots on the left side. I participated in the WeBank-AIRS collaboration project “Federated Reinforcement Learning”, led by Prof. Qiang Yang. (Nov. 2020-Oct. 2022)

Resource Optimization for Distributed Coordinated Multi-Point (CoMP) Systems This project aims to design optimal resource allocation strategies for improving the capacity of coherent and non-coherent CoMP systems over multiple wireless channels under hybrid power constraints. (Collaborated with Assoc. Prof. Brian Krongold and Dr. Phee Lep Yeoh) Representative publications: IEEE ICC 2017, IEEE GLOBECOM 2019, IEEE TCOM 2019, IEEE TGCN 2021

Resource Optimization for Distributed Cooperative Wireless Energy Harvesting Systems This project aims to design optimal energy beamforming strategies for improving the efficiency of distributed cooperative wireless power transfer (WPT) systems under hybrid power constraints. (Collaborated with Prof. Robert Schober, Assoc. Prof. Brian Krongold and Dr. Phee Lep Yeoh) Representative publications: ICC 2019, IEEE GLOBECOM 2019, IEEE TGCN 2022

Publications (Note: Student co-authors (co-)supervised by me are underlined)

Journal Papers

• B. Luo, X. Ouyang, P. Sun, P. Han, N, Ding, J. Huang, “Optimization Design for Federated Learning in Heterogeneous 6G Networks,” accepted in IEEE Network, 2023.

• B. Luo, PL. Yeoh, R. Schober and B. Krongold, “Distributed Energy Beamforming for Wireless Power Transfer over Frequency-Selective Fading Channels,” in IEEE Transactions on Green Communications and Networking, vol. 6, no. 4, pp. 2100-2114, Dec. 2022.

• B. Luo, PL. Yeoh, and B. Krongold, “Structural Properties of Optimal Power Allocation for DAS-OFDM under Joint Total and Individual Power Constraints,” IEEE Transactions on Green Communications and Networking, vol. 6, no. 1, pp. 530-542, March 2022.

• B. Luo, X. Li, S. Wang, J. Huang and L. Tassiulas, "Cost-Effective Federated Learning in Mobile Edge Networks," in IEEE Journal on Selected Areas in Communications, vol. 39, no. 12, pp. 3606-3621, Dec. 2021.

• B. Luo, PL. Yeoh, and B. Krongold, “Optimal Co-Phasing Power Allocation and Capacity of Coordinated OFDM Transmission with Total and Individual Power Constraints,” IEEE Transactions on Communications, vol. 67, no. 10, pp. 7103-7113, Oct. 2019.

• B. Luo, Q. Cui, and X. Tao, “Optimal Joint Water-Filling for Coordinated Transmission over Frequency-Selective Fading Channels,” IEEE Communication Letters, vol.15, no.2, pp.190-192, Feb. 2011.

• B. Luo, Q. Cui, X. Tao, and P. Zhang, “Closed Form Solutions of Joint Water-Filling for Coordinated Transmission,” IEICE Transactions on Communications, vol. 93-B, no. 12, pp. 3461-3468, Jan. 2010.

• Q. Cui, B. Luo, X. Huang and A.A. Dowhuszko, “Closed Form Solution for Minimizing Power Consumption in Coordinated Transmissions,” EURASIP Journal on Wireless Communications and Networking, vol. 2012, no. 122, Mar. 2012.

• Q. Cui, X. Huang, B. Luo and X. Tao, “Capacity Analysis and Optimal Power Allocation for Coordinated MIMO-OFDM Systems,” Science China Information Sciences, vol. 55, no. 6, pp.1372-1378, Jun. 2012.

Conference Papers

• J. Shao, S. Han, C. He, B. Luo, "Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data," in Workshop on Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities, in Conjunction with ICML 2023 (FL-ICML' 23), Jul. 2023.

• W. Xiao, T. Ye, B. Luo, J. Huang, "FedRos - Federated Reinforcement Learning for Networked Mobile-Robot Collaboration", accepted in Proc. IEEE International Conference on Distributed Computing Systems (ICDCS) Poster and Demo Session, Jul. 2023.

• B. Luo, Y. Feng, S. Wang, J. Huang, L. Tassiulas, “Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation”, accepted in Proc. IEEE International Conference on Distributed Computing Systems (ICDCS), 2023.

• B. Luo, W. Xiao, S. Wang, J. Huang, L. Tassiulas, “Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling”, in Proc. IEEE International Conference on Computer Communications (INFOCOM), 2022.

• B. Luo, X. Li, S. Wang, J. Huang, L. Tassiulas, “Cost-Effective Federated Learning Design,” in Proc. of IEEE International Conference on Computer Communications (INFOCOM), 2021.

• B. Luo, PL. Yeoh, R. Schober and B. Krongold, “Optimal Frequency-Selective Energy Beamforming with Joint Total and Individual Power Constraints”, in Proc. IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA, December, 2019.

• B. Luo, PL. Yeoh and B. Krongold, “Optimal Power Allocation for DAS-OFDM under Joint Total and Individual Power Constraints,” in Proc. IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA, December, 2019.

• B. Luo, PL. Yeoh, R. Schober and B. Krongold, “Optimal Energy Beamforming for Distributed Wireless Power Transfer over Frequency-Selective Channels,” in Proc. IEEE International Conference on Communications (ICC), Shanghai, China, May 2019.

• B. Luo, PL. Yeoh, and B. Krongold, “Optimal Co-phasing Power Allocation for Coordinated OFDM Transmission,” in Proc. IEEE International Conference on Communications (ICC), Paris, France, Jun. 2017.

• B. Luo, Q. Cui, X. Tao, and A.A. Dowhuszko, “On the Optimal Power Allocation for Coordinated Wireless Backhaul in OFDM Based Relay Systems,” in Proc. IEEE International Conference on Communications (ICC), Budapest, Hungary, Jun. 2013.

• B. Luo, Q. Cui, and X. Tao, “Constant-Power Joint Water-filling for Coordinated Transmission,” in Proc. IEEE Global Communications Conference (GLOBECOM), Houston, US, Dec. 2011.

• B. Luo, Q. Cui, H. Wang, and X. Tao, “Optimal Joint Water-filling for OFDM Systems with Multiple Cooperative Power Sources,” in Proc. IEEE Global Communications Conference (GLOBECOM), Miami, US, Dec. 2010.

• Q. Cui, B. Luo, and X. Huang, “Joint Power Allocation Solutions for Power Consumption Minimization in Coordinated Transmission System,” in Proc. IEEE Global Communications Conference (GLOBECOM) Workshop on Multi-Cell Cooperation, Houston, US, Dec. 2011.

Patents

• B. Luo, J. Shao, Method and Apparatus for Online Parameter Selection in Minimizing the Total Cost of Federated Learning, CN202310485067.8, Apr. 2023, field

• B. Luo, J. Shao, Method and Apparatus for Online Client Sampling in Minimizing the Training time of Federated Learning, CN 202310484383.3, Apr. 2023, field

• B. Luo, Y. Feng, J. Huang, Method and Apparatus for Stackelberg Game based Incentive Mechanism for Unbiased Federated Learning, CN CN202310489754.7, Apr. 2023, field

• B. Luo, J. Shao, J. Huang, Method and Apparatus for Frequent Items Mining Using Federated Analytics, CN202310365167.7, Mar. 2023, field

• B. Luo, J. Shao, J. Huang, Method and Apparatus for Frequent Data Mining Based on Hierarchical Federated Analytics, CN202310330791.3, Mar. 2023, field

• B. Luo, X. Li, J. Huang. Method and Apparatus for Dynamic Bandwidth Allocation in Heterogeneous Federated Learning, CN202211006603.3, August, 2022, field.

• B. Luo, Z. Li, J. Huang. Method and Apparatus for Measuring Client Contribuation in Federated Learning, CN202210509693.1, May, 2022, field.

• B. Luo, T. Ye, W. Xiao, J. Huang. Method and Apparatus for Model Aggregation for Federated Reinforcement Learning, CN202210320107.9, Mar. 2022, field.

• B. Luo, J. Sun, B. Tan, W. Jin and C. He. Method and Apparatus for Distributed Power Control in LTE-A system, CN103906200A, Jul. 2014, granted.

• Q. Cui, P. Zhang, X. Tao, B. Luo, A.A. Dowhuszko, and J. Hämäläinen. Method for allocating downlink transmission power of coordinated transmission devices in coordinated multi-point transmission system, U.S. Patent 8811147, Aug. 2014, granted.

Teaching

Undergraduate Course

• CS 101: Introduction to Computer Science (Fall 2022, 2023).

• CS 401: Cloud Computing (Spring 2023).

Graduate Course

• ECE 586: Vector Space Methods with Applications (Spring 2023).

Group

Principal Investigator (PI): Dr. Bing Luo

Ph.D. Students

• Jiaqi Shao (main supervised PhD student at HKUST, co-supervised with Prof. Xuanyu Cao)
• Xiang Li (co-supervised PhD student at CUHKSZ with Prof. Jianwei Huang)
• Langchen Liu (co-supervised PhD student at Yale with Prof. Lu Lu)

Master Students

• Yan Gong (co-supervised Master student at Wuhan University with Prof. Dazhao Cheng)
• Nanxi Wu (co-supervised Master student at Wuhan University with Prof. Chuang Hu)
• Tianyi Zhang

Research Assistants

• Zijun Sun (UESTC)
• Mingxi Li (Wuhan University)
• Shengguang Cui (CUHKSZ)
• Zihan Li (CUHKSZ)
• Yutong Feng (CUHKSZ)
• Sichang He
• Beilong Tang
• Renzo Balcazar
• Aicha Slaitane
• Boyan Zhang
• Tianjun Yuan

Alumni (Selected from main supervised research students)

• Wenli Xiao, research assistant, 2020-2022 → Master student at CMU Robotic Institute
• Tingwei Ye, research assistant, 2020-2022 → Master student at NYU Tandon School of Engineering
• Ziqi Li, research assistant, 2021-2022 → Master student at Oxford Mathematical Institute

Services

Conference (Technical) Program Committee Member

• IEEE ICC 2020-2023

• IEEE GLOBECOM 2020-2023

• IEEE ICDCS 2023

• NeurIPS - Federated Learning Workshop 2023

• NeurIPS - Federated Learning Workshop 2022

• ICML- Federated Learning Workshop 2021, 2023

• AAAI- Federated Learning Workshop 2022

• IJCAI- Federated Learning Workshop 2022

Journal Reviewer

• IEEE Journal on Selected Areas in Communications (JSAC)

• IEEE Transactions on Communications (TCOM)

• IEEE/ACM Transactions on Networking (ToN)

• IEEE Transactions on Mobile Computing (TMC)

• IEEE Transactions on Green Communications and Networking (TGCN)

• IEEE Transactions on Cognitive Communications and Networking (TCCN)

• IEEE Transactions on Network Science and Engineering (TNSE)

• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

• ACM Transactions on Intelligent Systems and Technology (TIST)

• IEEE Internet of Things Journal (IoT-J)

Selected Awards

• Joint Postdoctoral Fellowship, AIRS, CUHK(SZ) and Yale University (2020-2022)

• Melbourne Research Scholarship, Melbourne University (2016-2019)

• Kenneth Myers Memorial Scholarship, Melbourne University (2018-2019) (only one recipient every two years)

• Robert Bage Memorial Scholarship, Melbourne University (2017)

• Technical Innovation Expert Award, China Mobile (2015)

• Advanced LTE Technology Professionals Award, China Mobile (2014)

• Outstanding Master Thesis, BUPT (2012)

• Wu Tong Communications. Co., Ltd, Scholarship (2012)

• National First Grade Scholarship (2011)

• Meritorious Winner 24th US Mathematical Contest in Modeling (2008)