In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
By Xiaofei Wang, Yiwen Han, Chenyang Wang, Qiyang Zhao, Xu Chen, Min Chen. 2018
892 citations recorded by the source corpus.
Recently, along with the rapid development of mobile communication technology, edge computing theory and techniques have been attracting more and more attention from global researchers and engineers, which can significantly bridge the capacity of cloud and requirement of devices by the network edges, and thus can accelerate content delivery and improve the quality of mobile services. In order to bring more intelligence to edge systems, compared to traditional optimization methodology, and driven by the current deep learning techniques, we propose to integrate the Deep Reinforcement Learning techniques and Federated Learning framework with mobile edge systems, for optimizing mobile edge computing, caching and communication. And thus, we design the "In-Edge AI" framework in order to intelligently utilize the collaboration among devices and edge nodes to exchange the learning parameters for a better training and inference of the models, and thus to carry out dynamic system-level optimization and application-level enhancement while reducing the unnecessary system communication load. "In-Edge AI" is evaluated and proved to have near-optimal performance but relatively low overhead of learning, while the system is cognitive and adaptive to mobile communication systems. Finally, we discuss several related challenges and opportunities for unveili
Subfields: Artificial Intelligence, Computer Networks and Communications, Federated & Distributed Learning, ML Systems & Hardware
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Medhi Bennis
- Jihong Park
- H. Vincent Poor
- Mingzhe Chen
- Merouane Debbah
- Walid Saad
- Anis Elgabli
- Dusist Niyato
In Computer Networks and Communications
- Medhi Bennis
- Merouane Debbah
- Jihong Park
- Walid Saad
- H. Vincent Poor
- Mingzhe Chen
- Sumudu Samarakoon
- Anis Elgabli
In Federated & Distributed Learning
- Medhi Bennis
- H. Vincent Poor
- Jihong Park
- Sumudu Samarakoon
- Merouane Debbah
- Mingzhe Chen
- Walid Saad
- Qiang Yang
In ML Systems & Hardware
- H. Vincent Poor
- Medhi Bennis
- Jihong Park
- Anis Elgabli
- Mingzhe Chen
- Walid Saad
- Seong-Lyun Kim
- Xu Chen
Citations in the corpus
- Federated Learning With Differential Privacy: Algorithms and Performance Analysis (2019, background): “However, FL also poses several key challenges, such as private information leakage, expensive communication costs between servers and clients, and device variability [9]–[15].”
- Wireless Network Intelligence at the Edge (2018, methodology): “A similar procedure is applicable to deep Q-learning in MARL, where each agent approximates the Q values using an NN, as demonstrated in [184].”
- On Safeguarding Privacy and Security in the Framework of Federated Learning (2019, background): “In a concurrent development, artificial intelligence (AI) has revolutionized the ways that information is extracted with ground breaking successes in areas such as computer vision, natural language processing, voice recognition, etc [1].”
- Scheduling Policies for Federated Learning in Wireless Networks (2019, background): “Particularly, when the amount of training time is limited, solutions are taken by adapting the number of locally computing steps to the variance of global gradient [11], [15], [16], or scheduling the maximum number of UEs in a given time frame [10].”
- Federated Learning for Internet of Things: A Comprehensive Survey (2021, methodology): “[67] Edge data caching CFL DRL User equipments Edge/cloud server An edge caching scheme with DRL and FL.”
- Federated Learning in Edge Computing: A Systematic Survey (2022, methodology): “, the probability distribution of contents requested from all clients) [134], there is a common interest of all users in the network.”
- A Survey on Federated Learning for Resource-Constrained IoT Devices (2021, positive): “Besides, Wang et al. [11] designed a framework to exchange learning parameters of the clients through the collaboration for generating better local training models.”
- FedPD: A Federated Learning Framework With Adaptivity to Non-IID Data (2020, background): “However, such an assumption fails to hold for FL applications where the data (such as medical records, keyboards input data) are naturally generated by the individual agents [6, 1, 7, 8, 3, 9].”
- Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues (2020, positive): “[33] propose a FL framework for MEC systems for optimizing computing, caching and communications.”
- Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data (2019, methodology): “In federated learning systems, the raw data is collected and stored at multiple edge nodes, and a machine learning model is trained from the distributed data without sending the raw data from the nodes to a central place [27, 28].”
- Edge-Computing-Enabled Smart Cities: A Comprehensive Survey (2019, neutral): “However, the enabling of federated learning at the edge requires on-demand computational resources [93].”
- Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System (2019, background): “We set the range of (cid:15) to [1, 10].”
- A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks (2019, background): “First, the works in [7], [19], and [22] only provided a high-level exposition of the challenges of communication in FL.”
- Federated Learning in Smart City Sensing: Challenges and Opportunities (2020, neutral): “The goal is to design a machine learning framework that meets data privacy, security and regulatory requirements so that artificial intelligence systems can leverage the use of their data more efficiently and accurately [121].”
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019, background): “Indeed, the marriage of edge computing and AI has given rise to a new research area, namely, “edge intelligence (EI)” or “edge AI” [9], [10].”
- A Collaborative Learning Framework via Federated Meta-Learning (2020, background): “To address the above challenges, edge computing has recently emerged, and the marriage of edge computing and AI has given rise to a new research area, namely ‘edge intelligence’ or ‘edge AI’ [1] [2].”