7 papers
Federated Bilevel Performative Prediction
Liangxin Qian, Chang Liu, Xuanyu Cao +2
Federated bilevel optimization is widely used for nested learning problems across distributed clients, such as federated hyperparameter tuning and meta-learning under privacy and c…
A Unified Successive Approximation Framework for General Coupled Multiplicative and Fractional Optimization: HM-GM-AM-QM Transforms and Applications
Liangxin Qian, Wenhan Yu, Peiyuan Si +4
Optimization problems in communication networks and information systems often contain coupled multiplicative or fractional terms, such as sum-of-products, sum-of-ratios, and logari…
Parameter Training Efficiency Aware Resource Allocation for AIGC in Space-Air-Ground Integrated Networks
Liangxin Qian, Peiyuan Si, Jun Zhao +1
With the evolution of artificial intelligence-generated content (AIGC) techniques and the development of space-air-ground integrated networks (SAGIN), there will be a growing oppor…
QuHE: Optimizing Utility-Cost in Quantum Key Distribution and Homomorphic Encryption Enabled Secure Edge Computing Networks
Liangxin Qian, Yang Li, Jun Zhao
Ensuring secure and efficient data processing in mobile edge computing (MEC) systems is a critical challenge. While quantum key distribution (QKD) offers unconditionally secure key…
Enhancing Data Processing Efficiency in Blockchain Enabled Metaverse over Wireless Communications
Liangxin Qian, Jun Zhao
In the rapidly evolving landscape of the Metaverse, enhanced by blockchain technology, the efficient processing of data has emerged as a critical challenge, especially in wireless…
Private Transformer Inference in MLaaS: A Survey
Yang Li, Xinyu Zhou, Yitong Wang +2
Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service (MLaaS)…