Marie Siew
I'm currently a postdoctoral researcher in the Electrical and Computer Engineering Dept, Carnegie Mellon University, advised by Prof Carlee Joe-Wong. 
I obtained my PhD from the Singapore University of Technology and Design in 2021, advised by Prof Tony Quek and Dr Desmond Cai. Prior to that, I obtained my BSc. in Mathematical Sciences, from Nanyang Technological University, Singapore in 2016. 

In my research, I consider user-centric challenges in optimizing resource allocation in edge computing (EC), federated learning (FL) and other network + AI settings, given the user-centric nature of these technologies. To complement efficiency-driven solutions, together with my collaborators, we design user-centric decision making, resource allocation, optimization, and learning algorithms in EC and FL systems, with a focus on user incentives, resilience and fairness. 

My research has focused on the following themes: a) Incentive-aware Resource Sharing in Edge Computing. b) Resilient Resource allocation in Edge Computing, and c) Fairness and Incentives in Federated Learning. I am also actively exploring Human + AI joint decision making problems, both from the algorithmic perspective, and application driven (e.g. sustainability, smart cities) standpoint.​
​
Emails: marie_siew@alumni.sutd.edu.sg, msiew@andrew.cmu.edu
Google Scholar, LinkedIn
​
In my free time, I enjoy reading mystery novels, watercolor painting, cooking, exploring new restaurants and places, and watching movies!

Research Interests:
Edge Computing, Federated Learning, Resource Allocation, Reinforcement Learning, Network Economics, Game Theory, Distributed Optimization, Resilient Resource Allocation, Human-in the loop Learning.


Publications:
Working papers:
1. M. Siew, S. Sharma, Z. Li, K. Guo, C. Xu, T. Q. S. Quek and C. Joe-Wong, "FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations," to be submitted. [Preprint link].

2. M. Siew, Y. Hu, S. Sharma, Z. Li, L. Li, T. Lorido Botran, and C. Joe-Wong, "Towards Resilient Edge Computing: a Failure-Aware Reinforcement Learning Framework", to be submitted.

3. M. Siew, J. Park, Y. Liu, Y. Ruan, E. Zhang, L. Su, S. Ioannidis, E. Yeh, and C. Joe-Wong. 
Undisclosed Federated Learning Paper (Under review).

4. H. Yang*, M. Siew*, J.K.B. Lee, and C. Joe-Wong.
Undisclosed ML for Sustainability paper (Under review)

Conference Publications:
8.  S. Xie, M. Siew,  L. Li, Z. Chen, T. Yang, "Minimizing the THz Communication Outage Probability with ISAC for Delay-Sensitive Services", in Proc. IEEE Global Communications Conference (GLOBECOM), Kuala Lumpur, December 2023.

7. Y. Liu, L. Su, C. Joe-Wong, S. Ioannidis, E. Yeh, M. Siew "Cache enabled federated learning systems", in Proc. International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (ACM MobiHoc), Washington DC, October 2023. [Acceptance rate: 21.9%] [Link]

6. S. Gan, M. Siew, C. Xu and T. Q. S. Quek, "Differentially Private Deep Q-Learning for Pattern Privacy Preservation in MEC Offloading", in Proc. IEEE International Conference on Communications (ICC), Rome, May 2023. [Link] [Preprint Link]

5. M. Siew, S. Arunasalam, Y. Ruan, Z. Zhu, L. Su, S. Ioannidis, E. Yeh, and C. Joe-Wong, "Fair Training of Multiple Federated Learning Models on Resource Constrained Network Devices", in Proc ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN Posters, CPS-IoT Week), San Antonio, May 2023. Best Poster Award! [Link]

4. M. Siew, S. Sharma, and C. Joe-Wong, "ACRE: Actor Critic Reinforcement Learning for Failure-Aware Edge Computing Migrations", in Proc. IEEE Conference on Information Science and Systems (CISS), Baltimore, March 2023. [Link]

3. M. Siew, K. Guo, D. Cai, L. Li, and T. Q. S. Quek, "Let’s Share VMs: Optimal Placement and Pricing across Base Stations in MEC Systems," in Proc. IEEE International Conference on Computer Communications (INFOCOM), May 2021. [Acceptance rate: 19.9%] [Link],[Preprint LINK]

2. M. Siew, D. Cai, L. Li, and T. Q. S. Quek, “A Sharing-Economy Inspired Pricing Mechanism for Multi-Access Edge Computing,” in Proc. IEEE Global Communications Conference (GLOBECOM), Taipei, Dec 2020. [LINK]

1. L. Li, M. Siew, and T. Q. S. Quek, “Learning-Based Pricing for Privacy-Preserving Job Offloading in Mobile Edge Computing,” in Proc. IEEE International Conference on Accoustics, Speech and Signal Processing (ICASSP), Brighton, UK, May 2019. [LINK]

Journal Publications:
4. M. Siew, S. Sharma, K. Guo, D. Cai, W. Wen, C. Joe-Wong, T.Q.S Quek, "Towards Effective Resource Procurement in MEC: a Resource Re-selling Framework", IEEE Trans. Services Computing, 2023. [IEEE Xplore Early Access link]  [Preprint link]

3. X. Wu, J. Tang, and M. Siew, “Digital Twin-assisted Semi-Federated Learning Framework for Industrial Edge Intelligence,” China Communications, accepted, 2023.

2. L. Li, M. Siew, T. Q. S. Quek, and Z. Chen, “Optimal Pricing for Job Offloading in the MEC System with Two Priority Classes,” IEEE Trans. Vehicular Technology, vol. 70, no. 8, pp. 8080-8091, Aug. 2021. [LINK]

1. M. Siew, D. Cai, L. Li, T.Q.S. Quek, "Dynamic Pricing for Resource-Quota Sharing in Multi-Access Edge Computing", IEEE Trans. Network Science and Engineering, vol. 7, no. 4, pp. 2901-2912, Oct 2020. [LINK]

Book Chapters:
1. Z. Chen, L. Li, M. Siew, and T.Q.S. Quek. Edge/Fog Computing Networks. In Wiley 5G Ref, 2020. [LINK]