Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior

By Ali H. Sayed, Sheng-Yuan Tu, Jianshu Chen, Xiaochuan Zhao, Zaid J. Towfic. IEEE Signal Processing Magazine, 2013

488 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Networks and Communications, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/48181893e870a024de66f5277009edd925b622fc

How researchers see this paper

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

In Cognitive Neuroscience

In Computer Networks and Communications

In Statistical and Nonlinear Physics

Citations in the corpus

Robust Distributed Diffusion Recursive Least Squares Algorithms With Side Information for Adaptive Networks (2018, methodology): “This is based on the fact that the extension to CTA is straightforward by reversing the order of the adaptation and combination steps [2], [5].”
Adaptive Networks (2014, methodology): “For other applications in the areas of intrusion detection, online dictionary learning, target localization, spectrum sensing, sparse data recovery, and biological networks, the reader may refer to [1], [10]–[14], and the references therein.”
Distributed Policy Evaluation Under Multiple Behavior Strategies (2013, background): “In particular, the analysis in [20]–[22] shows that consensus networks combine local data and inneighborhood information asymmetrically, which can make the state of consensus networks grow unbounded even when all individual agents are mean stable in isolation.”
Robust Distributed Estimation by Networked Agents (2017, methodology): “We will compare the performance of the ATC diffusion LMS algorithm [8], [10]–[12], the ATC diffusion LMS algorithm with an adaptive combination policy [11], [42], and the ATC robust diffusion Fig.”
Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications (2021, methodology): “Typical decentralized aggregation approaches include the consensus-based methods [69] and diffusion strategies [70].”
Decentralized Federated Learning: A Survey and Perspective (2023, background): “The inspiration for the separation and clustering of network topologies comes from group behaviors observed in nature, such as ﬁsh schools and bee swarms [162].”
Multitask Diffusion Adaptation Over Networks (2013, background): “Accessible overviews of recent results in the ﬁeld can be found in [1], [2].”
Federated Learning With Cooperating Devices: A Consensus Approach for Massive IoT Networks (2019, methodology): “The negotiation stage (13)–(14) is similar to the diffusion strategy proposed in [30] and [31].”
Diff-DAC: Distributed Actor-Critic for Multitask Deep Reinforcement Learning (2017, background): “Diff-DAC differs from previous work on MDRL in that it follows a multiagent approach that leverages diffusion strategies for transferring knowledge between agents (Chen and Sayed 2013; Sayed et al. 2013; Sayed 2014a; Sayed 2014b).”