Distributed learning in wireless sensor networks

By Joel B. Predd, Sanjeev R. Kulkarni, H. Vincent Poor. IEEE Signal Processing Magazine, 2005

376 citations recorded by the source corpus.

This paper discusses nonparametric distributed learning. After reviewing the classical learning model and highlighting the success of machine learning in centralized settings, the challenges that wireless sensor networks (WSN) pose for distributed learning are discussed, and research aimed at addressing these challenges is surveyed.

Subfields: Computer Networks and Communications, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/b6139e7f568f0cbd8bcfc7dfd5885dec474270d6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Statistics and Probability

Citations in the corpus

On the Convergence of Decentralized Gradient Descent (2013, background): “These properties are important for applications where data are collected by distributed agents, communication to a fusion center is expensive or impossible, and/or agents tend to keep their raw data private; such applications arise in wireless sensor networks [16, 24, 27, 38], multivehicle and multi”
Multitask Diffusion Adaptation Over Networks (2013, background): “Section IV derives a stochastic gradient algorithm for distributed adaptive learning in a multitask-oriented environment.”
Distributed learning for Random Vector Functional-Link networks (2015, background): “So far, a large body of research has gone into developing fully distributed, decentralized learning algorithms, including works on diffusion adaptation [21,34], learning by consensus [16], distributed learning on commodity clusters architectures [8], adaptation on WSNs [5,32], distributed online lea”
Decentralized RLS With Data-Adaptive Censoring for Regressions Over Large-Scale Networks (2016, neutral): “Examples include wireless sensor networks, where a large number of inexpensive sensors cooperate to monitor, e.g. the environment [21], [22], or data centers, where a group of servers collaboratively handles dynamic user requests [24].”
Nested Distributed Gradient Methods with Adaptive Quantized Communication (2019, background): “Such problems arise in a plethora of applications such as wireless sensor networks [1], [2], multi-vehicle and multirobot networks [3], [4], smart grids [5], [6] and machine learning [7], [8], to mention a few.”
Adaptation, Learning, and Optimization over Networks (2014, background): “This scenario is also common in machine learning problems [4, 37, 85, 193, 234, 240] when data samples at the various agents are generated by a common distribution parameterized by some vector, wo.”
Communication-Efficient Distributed Online Prediction by Dynamic Model Synchronization (2014, background): “Examples are parallel data mining [23, 10] and M2M communication [20] where communication constitutes a performance bottleneck, learning with mobile sensors [16, 18] where communication drains battery power, and, most centrally, prediction-based real-time services [8] carried out by several servers,”
Adaptive Networks (2014, background): “This scenario is also common in machine learning problems [22], [23], [62]–[64] when data samples at the various agents are generated by a common distribution parameterized by some vector w o .”
Protocols for Learning Classifiers on Distributed Data (2012, methodology): “For distributed classiﬁcation, the dominant strategy (Predd et al., 2006; McDonald et al., 2010; Mann et al., 2009; Lazarevic & Obradovic, 2001) is to design local classiﬁers that work well on individual nodes.”
Machine Learning in Wireless Sensor Networks: Algorithms, Strategies, and Applications (2014, positive): “For such reasons, distributed and adaptive learning algorithms are adequate for in-network processing of data while avoiding exhausting the nodes with high computational tasks [145].”
Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior (2013, background): “This scenario is equally common in machine learning problems [73]–[76], where data samples often arise from the same underlying distribution.”
Balancing Communication and Computation in Distributed Optimization (2017, background): “This is motivated by its wide applicability to many important engineering and scientiﬁc domains such as, wireless sensor networks [1], [2], [3], [4], multi-vehicle and A. S. Berahas was with the Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL, USA.”
A Framework for Parallel and Distributed Training of Neural Networks (2016, background): “These problems are ubiquitous in the real world, and appear in many practical systems such as, e.g., wireless sensor networks (Predd et al., 2006), smart grids, distributed databases (Lazarevic and Obradovic, 2002), robotic swarms, just to name a few.”
Distributed compression-estimation using wireless sensor networks (2006, background): “P1 P 2 IEEE SIGNAL PROCESSING MAGAZINE [40] JULY 2006 distortion is achieved by separate source and channel coding.”