Room: MR 401
Abstract
The increasing complexity of modern wireless communication networks, particularly within multi-agent systems, demands innovative approaches to ensure sustainability, efficiency, and scalability. This workshop will delve into how the cross-integration of advanced technologies, including collaborative & adaptive learning models, AI/ML-driven optimization, generative AI, and quantum computing can drive sustainable solutions for multi-agent wireless networks and communications.
Collaborative and adaptive learning models, including federated, meta, and adaptive learning, enhance decentralized processing, real-time adaptation, and robustness in managing dynamic and complex network environments, such as the Internet of Things (IoT) and the Internet of Vehicles (IoV). When combined with AI/ML-based optimization, these models improve resource management and facilitate real-time decision-making in highly dynamic systems. Furthermore, integrating these technologies with neuromorphic computing enables ultra-low power, adaptive processing, optimizing wireless networks for human-centric communications that require personalized, low-latency interactions. Generative AI further contributes to sustainability by optimizing resource management, communication protocols, and data processing, especially when integrated with edge computing. This integration reduces energy consumption by enabling localized data processing, minimizing energy-intensive data transfers, and allowing multi-agent systems to dynamically adapt to changing network conditions. This ensures high performance and operational efficiency, even in resource-constrained environments. In parallel, AI-driven resource optimization, in combination with collaborative learning and generative AI, ensures efficient resource management in multi-agent networks, making them adaptable and sustainable. Additionally, the integration of quantum computing introduces new capabilities for solving complex optimization problems that are beyond the reach of classical computing. Hybrid quantum-classical systems enable more efficient resource management and faster decision-making, particularly in scenarios that require high computational power and precision, such as large-scale IoT networks.
By focusing on the cross-integration of these interconnected technologies, this workshop offers a comprehensive exploration of how they collectively contribute to the sustainability, scalability, and efficiency of multi-agent wireless networks. The workshop will provide valuable insights into developing practical and innovative solutions that can be applied in real-world scenarios.
The workshop will cover the latest advances and challenges in sustainable multi-agent wireless networks, focusing on collaborative & adaptive learning systems, generative AI, quantum-enhanced computing, and AI/ML-based strategies for network optimization. The topics of interest include edge computing, resource management, energy efficiency, security, and privacy, with a strong emphasis on the integration of AI, ML, and quantum technologies. This workshop stands out by emphasizing the cross-integration of advanced and emerging technologies to tackle complex challenges in wireless and multi-agent systems. Unlike the topics at main conference symposia that may focus on individual technologies, our approach fosters interdisciplinary dialogue and prioritizes practical solutions for IoT and IoV networks. This is aimed at researchers, engineers, and industry practitioners, providing a platform to exchange ideas, share insights, and explore future directions for next-generation wireless networks and communications.
Organizers
- Keshav Singh, National Sun Yat-sen University, Taiwan
- Omid Taghizadeh, Lenovo Deutschland GmbH, Germany
- Bishmita Hazarika, Memorial University, Canada
- M. Cenk Gursoy, Syracuse University, USA
WS15-S1:
Time: 09:00 – 10:30
Room: MR401
Chair: Keshav Singh
Presentations:
Keynote Talk (30 min)
Keynote Speaker: Prof. Sudhan Majhi
Topic: TBA
1571232644: Quantum-Enhanced Resource Allocation in Intelligent RAN Using Grover's Search Algorithm
Energy-Efficient Digital Twin-Driven Control for IoT-Centric Private 6G Networks
Mohamed Amine Hechmi
1571235802: Petsgram: An AI Enabled Pet First Social Matching Platform with Safety and Ethical Controls
Multi-Step Traffic Forecasting with Future-Guided Learning and Multi-Teacher Distillation
Vanchhit Khare
WS15-S2:
Time: 11:00 – 12:30
Room: MR401
Chair: Keshav Singh
Presentations:
1571236539: Machine-Learning-Based BPSK Decoding Under Fading Channels: A Comparative Study with Maximum Likelihood Detection
Silpa Priyadarsini Das; Manav Bhatnagar
1571237446: Digital Twin Predictive CSI for Downlink MISO-NOMA: A LSTM-Driven PPO Approach
Anal Paul; Keshav Singh
1571238611: PND3QN: A Deep Reinforcement Learning-Driven Routing Selection Framework for Network-on-Chip
JingWen Wang; Fang Yu; Xuecheng Sun; José T. de Sousa; Jiao Li
1571240918: Hybrid AI-Quantum Model with Attention-Guided Variational Circuits for MSSQL Attack Detection in Wireless Networks
Akshat Gaurav; Varsha Arya; Amiya Nayak; Kwok Tai Chui; Brij B. Gupta
1571241082: Joint Channel Estimation and Equalization for MU-MIMO-OFDM Uplink Based on Spatial-Temporal-Frequency GNN
Chi Jin; Feng He; Qian Zhang; Yongzhou Yang
1571241111: Hybrid Quantum-Classical Resource Slicing for eMBB and URLLC in O-RAN
Srikanta Dash; Keshav Singh; Sudip Biswas