IEEE International Conference on Communications
7-11 June 2020 // Virtual Conference
Communications Enabling Shared Understanding

WS-14: Workshop on Edge Machine Learning for 5G Mobile Networks and Beyond

WS-14: Workshop on Edge Machine Learning for 5G Mobile Networks and Beyond

WELCOME TO THE 1ST WORKSHOP ON "EDGE MACHINE LEARNING FOR 5G MOBILE NETWORKS AND BEYOND"

                                                                                           June 11, 2020, Dublin, Ireland

WORKSHOP CO-CHAIRS:

STEERING COMMITTEE MEMBERS:

  • Prof. Mérouane Debbah, IEEE Fellow, Huawei France Research Center and Mathematical and Algorithmic Sciences Lab, France
  • Prof. Zhu Han, IEEE Fellow, University of Houston, TX, USA
  • Prof. H. Vincent Poor, IEEE Fellow, Princeton University, NJ, USA

KEYNOTE SPEAKERS:

  • Prof. Mehdi Bennis, University of Oulu, Finland
  • Prof. Walid Saad, Virginia Tech, USA.

SCOPE AND TOPICS OF THE WORKSHOP

Machine learning and data-driven approaches have recently received much attention as a key enabler for future 5G and beyond wireless networks. To date, most existing learning solutions for wireless networks have relied on conventional machine learning approaches that require centralizing the training data and inference processes on a single data center. However, in future intelligent wireless networks, due to privacy constraints and limited communication resources for data transmission, it is impractical for all wireless devices that are engaged in learning to transmit all of their collected data to a data center that can subsequently use a centralized learning algorithm for data analytics or network self-organization. To this end, distributed edge learning frameworks are needed, to enable the wireless devices to collaboratively build a shared learning model with training their collected data locally. For wireless communication, edge machine learning admits many use cases. For example, distributed multi-agent reinforcement learning algorithms can be used to solve complex convex and nonconvex optimization problems that arise in various use cases such as network control, user clustering, resource management, and interference alignment. Moreover, distributed federated learning enables users to collaboratively learn a shared prediction model while remaining their collected data on their devices for user behavior predictions, user identifications, and wireless environment analysis. The field of edge machine learning is still at its infancy as there are many open theoretical and practical problems yet to be addressed, for edge machine learning, in general, and for wireless communication systems, in particular.

Thus, this full-day workshop will seek to bring together researchers and experts from academia, industry, and governmental agencies to discuss and promote the research and development needed to overcome the major challenges that pertain to this cutting-edge research topic. Suitable topics for this workshop include, but are not limited to, the following areas:

  • Fundamental limits of edge machine learning systems
  • Wireless network optimization for improving the performance of edge machine learning
  • Radio resource management for edge machine learning
  • Multiple access for edge machine learning
  • Data compression for edge machine learning
  • Adaptive transmission for edge machine learning
  • Techniques for wireless crowd labelling
  • Interference management in edge machine learning networks
  • Emerging theories and techniques such as age of information and blockchain for edge machine learning
  • Modeling and performance analysis of edge machine learning networks
  • Energy efficiency of implementing machine learning over wireless edge networks
  • Ultra-low latency edge machine learning
  • Data analytics driven wireless communication
  • Multi-agent reinforcement learning for intelligent network control and optimization
  • Network architectures and communication protocols for edge machine learning
  • Experimental testbeds and techniques of edge machine learning
  • Privacy and security issues of edge machine learning
  • Edge machine learning for intelligent signal processing, e.g., signal detection
  • Edge machine learning for mobile user behavior analysis and inference
  • Edge machine learning for emerging applications, e.g., vehicle to everything (V2X), UAV-enabled communication, Internet of Things, intelligent reflecting surface (IRS), Massive MIMO, virtual reality (VR), and augmented reality (AR)

IMPORTANT DATES

Paper submission February 1, 2020
Notification of acceptance February 28, 2020
Final papers submission March 1, 2020
Workshop date June 11, 2020

 

Schedule on June 11, 2020

Time

Event

16:00 to 19:30 in Dublin, 11:00-14:30 in NY, 23:00-02:30 in China

Keynote on Edge Learning, Speakers: Walid Saad, Mehdi Bennis

17:50 to 19:30 in Dublin, 12:50-14:30 in NY, 00:50-02:30 in China

Session 1: Federated Learning over Wireless Networks

20:00 to 21:40 in Dublin, 15:00-16:40 in NY, 03:00-04:40 in China

Session 2: Reinforcement Learning for Wireless Networks

21:50 to 23:30 in Dublin, 16:50-18:30 in NY, 04:50-06:30 in China

Session 3: Machine Learning for Wireless Networks

 

Detailed Arrangement of Each Session

Session 1: Federated Learning over Wireless Networks

Time: 17:50 to 19:30 in Dublin, 12:50-14:30 in NY, 00:50-02:30 in China

Six Papers:

  1. Chenyuan Feng; Yidong Wang; Zhongyuan Zhao; Tony Q. S. Quek; Mugen Peng; “Joint Optimization of Data Sampling and User Selection for Federated Learning in the Mobile Edge Computing Systems”.
  2. Qunsong Zeng; Yuqing Du; Kaibin Huang; Kin K. Leung; “Energy-Efficient Radio Resource Allocation for Federated Edge Learning”.
  3. Naifu Zhang; Meixia Tao; “Gradient Statistics Aware Power Control for Over-the-Air Federated Learning in Fading Channels”.
  4. Donghui Ma; Lixin Li; Huan Ren; Dawei Wang; Xu Li; Zhu Han; “Distributed Rate Optimization for Intelligent Reflecting Surface with Federated Learning”.
  5. Yining Wang; Yang Yang; Tao Luo; “Federated Convolutional Auto-encoder for Optimal Deployment of UAVs with Visible Light Communications”.
  6. Umair Yaqub Mohammad; Sameh Sorour; Mohamed S Hefeida; “Task Allocation for Mobile Federated and Offloaded Learning with Energy and Delay Constraints”.

Session 2: Reinforcement Learning for Wireless Networks

Time: 20:00 to 21:40 in Dublin, 15:00-16:40 in NY, 03:00-04:40 in China

Six Papers:

  1. Nikita Tafintsev; Dmitri Moltchanov; Meryem Simsek; Shu-ping Yeh; Sergey Andreev; Yevgeni Koucheryavy; Mikko Valkama; “Reinforcement Learning for Improved UAV-based Integrated Access and Backhaul Operation”.
  2. Dian Tang; Xuefei Zhang; Meng Li; Xiaofeng Tao; “Adaptive Inference Reinforcement Learning for Task Offloading in Vehicular Edge Computing Systems”.
  3. Md Moin Uddin Chowdhury; Walid Saad; Ismail Güvenç; “Mobility Management for Cellular-Connected UAVs: A Learning-Based Approach”.
  4. Zhiyang Li; Ming Chen; Kezhi Wang; Cunhua Pan; Nuo Huang; Yuntao Hu; “Parallel Deep Reinforcement Learning based Online User Association Optimization in Heterogeneous Networks”.
  5. Dawei Chen; Yifei Wei; Li Wang; Choong Seon Hong; Li-Chun Wang; Zhu Han; “Deep Reinforcement Learning Based Strategy for Quadrotor UAV Pursuer and Evader Problem”.
  6. Jie Yan; Yanxiang Jiang; Fu-Chun Zheng; Richard Yu; Xiqi Gao; Xiaohu You; “Distributed Edge Caching with Content Recommendation in Fog-RANs via Deep Reinforcement Learning”.

Session 3: Machine Learning for Wireless Networks

Time: 21:50 to 23:30 in Dublin, 16:50-18:30 in NY, 04:50-06:30 in China

Six Papers:

  1. Mounir Bensalem; Jasenka Dizdarević; Admela Jukan; “Modeling of Deep Neural Network (DNN) Placement and Inference in Edge Computing”.
  2. Zhong Yang; Yuanwei Liu; Yue Chen; “Distributed Reinforcement Learning for NOMA-Enabled Mobile Edge Computing”.
  3. Jiawei Shao; Jun Zhang; “BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems”.
  4. Sabur Baidya; Peyman Tehrani; Marco Levorato; “Data-Driven Path Selection for Real-Time Video Streaming at the Network Edge”.
  5. Jun Zong; Fuqian Yang; Xiliang Luo; “Optimal Query Policy and Task Offloading in Dynamic Environments”.
  6. Dongzhu Liu; Guangxu Zhu; Jun Zhang; Kaibin Huang; “Exploiting Diversity Via Importance-Aware User Scheduling For Fast Edge Learning”.

Patrons

Exhibitors

Supporters