​




林柏呈 Frank Po-Chen Lin, PhD​

Area of Interest
Scalable Machine Learning, Cloud/Edge Intelligence, Optimization, Convergence Analysis, Federated Learning and Differential Privacy.

Education
Ph.D. Purdue University, USA        Aug. 2019 to Aug. 2023
- Major: Electrical and Computer Engineering (ECE)
- Thesis: Distributed Machine Learning over Large-scale Networks (Advisor: Prof. Nicolò Michelusi and Prof. Christopher Brinton)

M.S. National Taiwan University (NTU), Taiwan       Sept. 2016 to June 2018
- Major: Electrical Engineering (Communication Engineering)
- Thesis: A Hierarchical Edge-Cloud SDN Controller System with Optimal Resource Allocations for Load-Balancing (Advisor: Prof. Zsehong Tsai)
​
B.S. National Sun Yat-sen University (NSYSU), Taiwan       Sept. 2012 to June 2016
- Major: Electrical Engineering
- Independent Study: Approaches with Sparse Perfect Gaussian Integer Sequences for Physical Layer Security in Wireless Network (Advisor: Prof. Chih-Peng Li)
Honor & Distinctions
  • Frederick N. Andrews Fellowship, ECE, Purdue University, USA.                             2019 to 2023
                     -4-year fellowship for outstanding PhD-track students at Purdue University
  • College Student Research Creativity Award, Ministry of Sci. and Tech., Taiwan.                    2016          -200 out of 7129 candidates in undergraduate independent studies (Nationwide Competition)
  • Graduate with Honor (榮譽畢業生) from NSYSU.                                                                   2016 
  • Graduate Representative (電機系畢業生代表) of NSYSU EE.                                                2016
  • Presidential Award (Top 3 in the department, 書卷獎), EE, NSYSU, Taiwan.             2013 to 2016           -Rank top 3 in the Department of EE for every semester from 2013 to 2016
  • Scholarship of Advanced Semiconductor Engineering, Inc.                                                      2016
Leadership Experiences
  • President of Taiwanese Graduate Student Association (台灣研究生學生會會長), ​                    Purdue University, USA.                                                                                              2020-2021 
  • Host of Gaming Night Program, English Learning Plaza, NSYSU, Taiwan.                        2014
  • Host of Easter Party Program, English Learning Plaza, NSYSU, Taiwan.                            2014
  • Captain of Honor Guard (儀隊隊長), Zhongzheng Senior High School, Taiwan.        2010-2011

Professional Society Activities 
    Reviewer for the following Journals and Conference proceedings 
       - IEEE Transactions on Signal Processing 
​       - IEEE Transactions on Mobile Computing  
       - IEEE Journal on Selected Areas in Communications
       - IEEE Transactions on Wireless Communications 
       - IEEE Transactions on Communications ​
       - IEEE Communications​ Magazine
       - IEEE Access
       - IEEE International Conference on Computer Communications (IEEE INFOCOM)
       - IEEE Global Communications Conference (IEEE Globecom)
Research Publications
Journals:
  1. [J1] Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton and Nicolò Michelusi, “Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregations," IEEE Journal on Selected Areas in Communications, vol. 39, pp. 3851 - 3869, 2021.​
  2. [J2] Frank Po-Chen Lin and Zsehong Tsai, Hierarchical Edge-Cloud SDN Controller System with Optimal Resource Allocation for Load-Balancing," IEEE Systems Journal, vol. 14, 265-276, 2020. (Q1, SCIE, 10/148)
  3. [J3] Frank Po-Chen Lin and Frederick Kin Hing Phoa, Runtime Estimation and Scheduling on Parallel Processing Supercomputers via Instance-based Learning and Swarm Intelligence," International Journal of Machine Learning and Computing, vol. 9, 592-598, 2019. 
  4. [J4] Frank Po-Chen Lin and Frederick Kin Hing Phoa, “An Efficient Construction of Confidence Bands via Swarm Intelligence and its Application in Target Localization,” IEEE Access, vol. 6, 8610 - 8618, 2018. (Q1, SCIE, 24/148)
Conference Proceedings:
  1. ​[C1] Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton and Nicolò Michelusi, “Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling,"in Proc. IEEE Global Communications Conference (Globecom), Dec, 2021.
  2. [C2] Frank Po-Chen Lin, C. Brinton and N. Michelusi, "Federated Learning with Communication Delay in Edge Networks," in Proc. IEEE Global Communications Conference (Globecom), Dec. 2020.
  3. [C3] Frank Po-Chen Lin and Frederick Kin Hing Phoa, “A performance study of parallel programming via CPU and GPU on swarm intelligence based evolutionary algorithm,” International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ACM-ISMSI 2017), Hong Kong, China, March 25-27, 2017. (indexed by EI and Scopus)
  4. [C4] Sen-Hung Wang, Frank Po-Chen Lin, and Chih-Peng Li, “Secure channel estimation method in TDD OFDM systems,” Proc. 2016 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (IEEE BMSB 2016), Nara, Japan, June 1-3, 2016.
  5. [C5] David Nickel, Frank Po-Chen Lin, Seyyedali Hosseinalipour, Nicolo Michelusi and Christopher G Brinton, “Resource-Efficient and Delay-Aware Federated Learning Design under Edge Heterogeneity,” 2022 IEEE International Conference on Communications Workshops (ICC Workshops), Seoul, South Korea, May 16-20, 2022. 

Research Experience 
School of Electrical and computer engineering at Purdue University. 2019 to current
- Design of scalable machine learning algorithms:
Design learning algorithms based on mathematical analysis to efficiently solve a general class of machine learning problems over large-scale networks. ([J1], [C1], [C2])
​- Characterizing the design of learning parameters:
Theoretical analysis on the the learning algorithm to reveal the optimal decision of tunable learning parameters and its effect on the learning performance. ([J1], [C1], [C2])
                                                (Advisor: Dr. Christopher Brinton, Dr. Nicolò Michelusi)
Institute of Communications Engineering in NTU. 2016 to 2018
- Architecture Design for Large-Scale SDN Structure:
Developed a Hierarchical SDN system with a new load-balancing algorithm. Simulation results shows that the system provides outstanding results in both delay and fairness in large-scale network. ([J2])
- Queueing Model Design for SDN:
Developed a simulation model for Hierarchical SDN systems using queueing theory. Mathematical models can be efficiently derived according to the requirements of the network. ([J2])
- Evolutionary Algorithm Design for Community Detection:
Developed a swarm intelligence-based community detection algorithm. Computation Complexity is highly reduced and different scales of communities can be revealed through designs of particle update in each iteration.
                                                                                                               (Advisor: Dr. Zsehong Tsai)

Institute of Statistical Science in Academia Sinica. 2015 to 2018
- Scheduling Design for Supercomputers:
Propose and implement an effective learning and scheduling algorithm design on the ALPS supercomputer. Simulation results on various job arrivals show that our algorithm outperforms the state-of-the-art approaches with at least 100-times speedup. ([J3])
- Trajectory Localization:
Design a trajectory localization evolutionary algorithm to construct the confidence regions of target trajectory. The moving speed of the trajectory can be easily inferred from the state of the confidence regions without additional hardware. ([J4])
- Parallel Design on Evolutionary Algorithms:
Developed a parallizable structure for swarm intelligence-based evolutionary algorithm. The proposed work offers a good approach for parallel evolutionary computation on CPU. ([C3])
                                                                                         (Advisor: Dr. Frederick Kin Hing Phoa)

Department of Electrical Engineering in NSYSU 2015 to 2016
- Wireless Security Design for Eavesdroppers in OFDM systems:
Developed a low-complexity cryptography encryption method and a simple four-phase channel estimation scheme to provide secure channel. Simulation results demonstrates that the eavesdropper can not obtain any information about transmitted data even located near a legitimate transmitter. ([C4])
​                                                                                                               (Advisor: Dr. Chih-Peng Li)

Working Experiences 
  • Research Assistant, School of ECE, Purdue University                                     2021 to current
  • Teaching Assistant, Graduate Institute of Electrical Engineering, NTU                              2019
  • R.O.C. Military Police (中華民國憲兵), Military Police Training Center             2018 to 2019
  • Research Assistant, Institute of Statistical Science, Academia Sinica                   2015 to 2018
  • Research Assistant, Institute of Communication Engineering, NTU                     2016 to 2018
  • Teaching Assistant, International School of Taiwan Comprehensive Uni. System            2014
  • English Tutor, English Learning Plaza, NSYSU                                                    2012 to 2014
  • Summer Intern, Taipei Computer Association                                                                    2013

Mentor
        Dr. Jacob C. Huang
  • Inspired my professional English technical writing skills
  • Provided valuable detail advises on my decision of studying abroad
  • Recommended and lent me various inspiring books to broaden my horizon 
  • Gave illuminating suggestions on possible directions of my independent study
  • Invited me to research-related awarding ceremonies to grasp better understandings on the great attitudes and intriguing methodologies of those outstanding researchers
  • Continuously taking care of me and giving strong encouragements to me on my lifelong career