Publication
(** denotes equal contributions)
Yang, Mengwei, Buyukates, Baturalp, and Shen, Yanning, and Markopoulou, Athina, “Valuing Solo and Synergy in Federated Learning”, Under submission.
Yang, Mengwei, Buyukates, Baturalp, and Markopoulou, Athina, “Rewarding the Rare: Maverick-Aware Shapley Valuation in Federated Learning”, Under submission.
Chu, Tianyue*, Yang, Mengwei*, Laoutaris, Nikolaos, and Markopoulou, Athina, “PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learning”, accepted to Transactions on Modeling and Performance Evaluation of Computing Systems (ToMPECS), October 2024.
Yang, Mengwei, Jarin, Ismat, Buyukates, Baturalp, Avestimehr, Salman, Markopoulou, Athina, “Maverick-Aware Shapley Valuation for Client Selection in Federated Learning”, poster in ISIT workshop on “Informational Theoretic methods for Trustworthy ML” (IT-TML), July 7th 2024, Athens, Greece.
Chu, Tianyue, Yang, Mengwei, Laoutaris, Nikolaos, and Markopoulou, Athina, “Information-Theoretical Bounds on Privacy Leakage in Pruned Federated Learning”, poster and presentation, ISIT workshop on “Informational Theoretic methods for Trustworthy ML” (IT-TML), July 7th 2024, Athens, Greece
Bakopoulou, Evita*, Yang, Mengwei*, and Zhang, Jiang and Psounis, Konstantinos and Markopoulou, Athina, “Location leakage in federated signal maps.”, in IEEE Transactions on Mobile Computing, vol. 23, no. 06, pp. 6936-6953, June 2024.
Zong, Zixiao and Yang, Mengwei and Ley, Justin and Butts, Carter T and Markopoulou, Athina, “Privacy by projection: Federated population density estimation by projecting on random features.”, in Proceedings on Privacy Enhancing Technologies (PoPETs), 2023(1), Lausanne, Switzerland, July 2023.
Yang, Mengwei and Liu, Shuqi, Xu, Jie, Tan, Guozhen, Li, Congduan, and Song, Linqi. “Achieving privacy-preserving cross-silo anomaly detection using federated XGBoost.” Journal of the Franklin Institute 360, no. 9 (2023): 6194-6210.
Yang, Mengwei and Song, Linqi and Xu, Jie and Li, Congduan and Tan, Guozhen, “The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost”, accepted and to appear in IJCAI Workshop: International Workshop on Federated Machine Learning for User Privacy and Data Confidentiality (IJCAI-FL 2019).