Wireless Network Intelligence at the Edge

By Jihong Park, Sumudu Samarakoon, Medhi Bennis, Merouane Debbah. 2018

588 citations recorded by the source corpus.

Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory, and computing resources, limiting their adoption for resource-constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, and so on) requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data are unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover, training and inference are carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented to demonstrate the effectiveness of edge ML in unlocking the full potential of 5G and beyond.

Subfields: Artificial Intelligence, Computer Networks and Communications, 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

In Computer Networks and Communications

In ML Systems & Hardware

Citations in the corpus

Why Should We Add Early Exits to Neural Networks? (2020, background): “Secondly, in the inference phase, these networks are complex to implement in resource-constrained or distributed scenarios [32, 53].”
Advances and Open Problems in Federated Learning (2019, background): “Potential solutions to address this challenge include federated distillation (FD), in which workers exchange their model output parameters (logits) as opposed to the model parameters (gradients and/weights), and optimizing workers’ scheduling policy with appropriate communication and computing resou”
FedML: A Research Library and Benchmark for Federated Machine Learning (2020, methodology): “Applications of this model to wireless edge devices are described in [127, 128].”
Adaptive Federated Learning in Resource Constrained Edge Computing Systems (2018, background): “This variant of distributed machine learning (model training) from a federation of edge nodes is known as federated learning [8]–[10].”
Scheduling Policies for Federated Learning in Wireless Networks (2019, background): “…usually access points (APs), future networks will be able to utilize local data to conduct intelligent inference and control on many activities, e.g., learning activities of mobile phone users, predicting health events from wearable devices, or detecting burglaries within smart homes [5], [6].”
Distributed Learning in Wireless Networks: Recent Progress and Future Challenges (2021, background): “[24], and are mostly qualitative with a few exceptions [17], [24], [25].”
Distilling On-Device Intelligence at the Network Edge (2019, methodology): “Theoretical and algorithmic enablers of on-device ML are overviewed in [1].”
Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning (2020, background): “Therefore, FL becomes a promising technology for distributed data analysis and model training in wireless networks [9], [10], and has been used in many applications, for instance, resource allocation optimization in vehicle-to-vehicle (V2V) communications [11] and content recommendations for smartph”
Convergence Time Optimization for Federated Learning Over Wireless Networks (2020, background): “However, implementing FL over wireless networks faces several challenges [4]–[6], such as selection of users for FL, energy efficiency of FL implementation, computational resource allocation for training FL models at edge devices, spectrum resource allocation for FL parameter transmission, and desig”
Massive Autonomous UAV Path Planning: A Neural Network Based Mean-Field Game Theoretic Approach (2019, background): “Collaborative HJB and FPK model training across UAVs via federated learning frameworks [17] could thus be an interesting topic for future work.”
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air (2019, background): “Communication is typically more costly compared to processing; therefore, a much more desirable and practically viable alternative is to develop distributed ML techniques that can exploit the local processing capabilities of edge devices, requiring limited communications (see [1] for a survey of app”
Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMM (2020, methodology): “Federated learning is one representative method that ensures learning through periodically exchanging model parameters across workers rather than sending private data samples (McMahan et al., 2017; Kairouz et al., 2019; Park et al., 2019b).”
A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems (2019, background): “To perform these critical application tasks, low-latency, high-reliability and scalable AI is needed, along with a reliable infrastructure [1] and [3].”
Coded Federated Computing in Wireless Networks with Straggling Devices and Imperfect CSI (2019, unknown): “These include wireless data centers [2], in which the processors are conventional servers, and federated learning [4], [5], in which computing is carried out collaboratively by mobile devices.”
Edge Learning for B5G Networks With Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing (2022, unknown): “vides a unified framework to fully utilize communication theory, offer fundamental privacy and security guarantees, and reap promised performance gains for ML at network edges [111].”
Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications (2020, background): “With wireless connectivity, distributed learning frameworks have been overviewed in [13], [28], and [29].”