CREWS achieves robust collaborative WiFi sensing under node dropout and asynchronous arrivals via a cardinality-normalized set aggregator, elastic parameter alignment, and staleness-aware adaptive feature replay, with a proven joint convergence guarantee.
The weights1 /(1 +๐ ๐ก ) and ๐๐ก /(1 +๐ ๐ก ) sum to one, so ห๐๐ก is a convex combination of the fresh and replay gradients
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CREWS: Collaborative Robust Edge WiFi Sensing with Asynchronous and Incomplete Observations
CREWS achieves robust collaborative WiFi sensing under node dropout and asynchronous arrivals via a cardinality-normalized set aggregator, elastic parameter alignment, and staleness-aware adaptive feature replay, with a proven joint convergence guarantee.