Timely Communication
Timely communication, encompassing efficient information exchange and coordinated action, is a crucial research area impacting diverse fields from AI to healthcare. Current research focuses on optimizing communication efficiency in distributed systems like federated learning, employing techniques such as scalar communication, zero-order optimization, and lossy compression to reduce bandwidth and energy consumption. This work also explores the development of robust communication strategies in noisy environments and the integration of AI, particularly LLMs, to enhance understanding and improve the efficiency of communication in various applications, including human-robot collaboration and crisis response. The resulting advancements have significant implications for improving the performance and scalability of AI systems, optimizing resource utilization in communication networks, and enhancing human-computer and human-robot interaction.
Papers
FedNet2Net: Saving Communication and Computations in Federated Learning with Model Growing
Amit Kumar Kundu, Joseph Jaja
Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications
Deniz Gunduz, Zhijin Qin, Inaki Estella Aguerri, Harpreet S. Dhillon, Zhaohui Yang, Aylin Yener, Kai Kit Wong, Chan-Byoung Chae
AutoQML: Automated Quantum Machine Learning for Wi-Fi Integrated Sensing and Communications
Toshiaki Koike-Akino, Pu Wang, Ye Wang
Mobility, Communication and Computation Aware Federated Learning for Internet of Vehicles
Md Ferdous Pervej, Jianlin Guo, Kyeong Jin Kim, Kieran Parsons, Philip Orlik, Stefano Di Cairano, Marcel Menner, Karl Berntorp, Yukimasa Nagai, Huaiyu Dai