Effect of compression on reconstruction quality under random communication topology.

Gespeichert in:
Bibliographische Detailangaben
Titel: Effect of compression on reconstruction quality under random communication topology.
Autoren: Victoria Erofeeva, Oleg Granichin, Vikentii Pankov, Zeev Volkovich
Publikationsjahr: 2025
Schlagwörter: Cell Biology, Infectious Diseases, Biological Sciences not elsewhere classified, Mathematical Sciences not elsewhere classified, Information Systems not elsewhere classified, world datasets show, unlike traditional methods, trained neural network, dynamic network changes, system &# 8217, minimal communication overhead, efficient decentralized clustering, system adapts, clustering structure, clustering accuracy, %22">xlink ">, static topologies, paper presents, iot ), immediate results, highly suitable, generate compact, fly processing, dynamical multi, distributed environments, distributed aggregation, dimensionality reduction, data must, consistent summaries, consensus protocol
Beschreibung: The plot shows the relationship between clustering quality (measured by relative mean absolute error between predicted and ground-truth centroids) and the total transmitted information volume across all agents. Two compression modes are evaluated: 14x and 7x. The shaded areas represent variance across 30 runs with random topologies, where each pair of agents has a 0.02 probability of being connected.
Publikationsart: still image
Sprache: unknown
Relation: https://figshare.com/articles/figure/Effect_of_compression_on_reconstruction_quality_under_random_communication_topology_/29667954
DOI: 10.1371/journal.pone.0327396.g002
Verfügbarkeit: https://doi.org/10.1371/journal.pone.0327396.g002
https://figshare.com/articles/figure/Effect_of_compression_on_reconstruction_quality_under_random_communication_topology_/29667954
Rights: CC BY 4.0
Dokumentencode: edsbas.E741334B
Datenbank: BASE
Beschreibung
Abstract:The plot shows the relationship between clustering quality (measured by relative mean absolute error between predicted and ground-truth centroids) and the total transmitted information volume across all agents. Two compression modes are evaluated: 14x and 7x. The shaded areas represent variance across 30 runs with random topologies, where each pair of agents has a 0.02 probability of being connected.
DOI:10.1371/journal.pone.0327396.g002