Abstract

The proliferation of wireless devices and the increasing demand for wireless services, coupled with inefficient spectrum allocation and limited spectrum availability, exacerbate the scarcity of wireless spectrum resources in next-generation (NextG) networks. This project focuses on the development of novel transfer learning (TL) frameworks for dynamic spectrum sharing (DSS) to enable knowledge transfer across users, environments, and wireless systems, offering viable approaches to intelligently utilize underutilized licensed spectrum more effectively. DSS wireless systems exhibit characteristics such as dynamic environments, heterogeneous networks, massive connections, interference, high communication overhead, limited computing, and storage capacity, as well as security and privacy concerns, making it challenging to learn and leverage transferable knowledge. Moreover, achieving the desired performance of knowledge transfer often requires substantial amounts of high-quality training data, while transferring data knowledge may raise security and privacy issues, limiting adaptation and generalization to other tasks. Therefore, this project aims to explore novel TL strategies for learning transferable knowledge and addressing concerns related to robustness, efficiency, security, and privacy in DSS systems.  

A key thrust of the project involves a systematic investigation into the characteristics and parameters of target DSS wireless systems, alongside an exploration of the fundamental principles, theories, and unique challenges associated with knowledge transfer. These studies aim to bridge the gap between system characteristics and algorithm development. Based on the findings, the research team will (1) design an ensemble evaluation scheme to assess the robustness, efficiency, security, and privacy of TL-based DSS frameworks, (2) develop efficient TL-based DSS frameworks for adaptive spectrum sensing, selection, access, and handoff, and (3) create robust security and privacy TL strategies for monitoring, detecting, mitigating, and preventing various malicious attacks, while also protecting sensitive data. Concurrently, the research team will develop a Wireless Knowledge Transfer testbed that incorporates transferable knowledge, evaluation schemes, pre-trained TL models, attack knowledge databases, and security and privacy strategies. This testbed is to facilitate and standardize research on knowledge reuse in wireless communication systems. The integration of research and education plans will equip the NextG workforce in the fields of DSS, artificial intelligence, transfer learning, and cybersecurity. Outreach activities will establish connections between the DSS research, and minority groups, K-12 students, and college students through various learning approaches. 

• Ziyu Wang, Yiming Du, Rui Ning, Daniel Takabi, and Lusi Li*. “ECSC: Energy-Calibrated Semantic Communication.” IEEE MILCOM 2025 (in press). [code]

• Yao Wang, Chunyu Hu, Jian Li, Rui Ning, Lusi Li*, and Daniel Takabi. “Contrastive Multi-Hop Semantic Communication.” IEEE MILCOM 2025 (in press). 

• Ziyu Wang, Yiming Du, Rui Ning, and Lusi Li*. "Energy-based Deep Incomplete Multi-View Clustering." Proceedings of the 33rd ACM International Conference on Multimedia 2025  (in press). [code]

• Ziyu Wang, Yiming Du, Yao Wang, Rui Ning, and Lusi Li*. "Deep Incomplete Multi-view Clustering via Multi-level Imputation and Contrastive Alignment." Neural Networks 181 (2025): 106851. [paper] [code]

• Tao, Qian, Chenghao Liu, Yuhan Xia, Yong Xu, and Lusi Li*. "Adaptive multi-graph contrastive learning for bundle recommendation." Neural Networks 181 (2025): 106832. [paper]

• Jiawei Chen, Lusi Li, Daniel Takabi, Masha Sosonkina, and Rui Ning. “Heterogeneous Graph Backdoor Attack.” IEEE Symposium on Security and Privacy (S&P 2026) (under review). [paper]

• Leizhen Zhang, Lusi Li, Di Wu, Sheng Chen, and Yi He. “Fairness-Aware Streaming Feature Selection with Causal Graphs.” In 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC). [paper] [code]

• Lusi Li*, Rui Ning, Ziyu Wang, and Shuai Hao. "A Dual Transfer Framework for Cooperative Spectrum Sensing in Cognitive Radio." In 2024 International Conference on Computing, Networking and Communications (ICNC), pp. 1065-1070. IEEE, 2024. [paper]

• Qian Tao, Jianpeng Liao, Enze Zhang, Lusi Li*. "A Dual Robust Graph Neural Network Against Graph Adversarial Attacks." Neural Networks, 175 (2024): 106276. [paper]

• Ziyu Wang, Lusi Li*, Xin Ning, Wenkai Tan, Yongxin Liu, and Houbing Song. "Incomplete Multi-view Clustering via Structure Exploration and Missing-view Inference." Information Fusion (2024): 102123. [paper] [code]

• Judge: AI track of the Great Computer Challenge (GCC) for K-12 students (2024, 2025)

• Judge: CSGS Hackathon Event

• Panelist: AI Q&A Panel of ACM

• Advisor: Association for Computing Machinery Women (ACM-W) (2022-present)