Introduces staleness-bucket aggregation with padding for distributed perceptron and proves finite-horizon mistake bounds where delay affects only mean staleness and noise adds a sqrt(horizon) term.
Federated learning via over- the-air computation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Analog RF computing performs neural network matrix-vector multiplications via RF waveform mixing at clients in MU-MIMO systems, reducing energy consumption by nearly two orders of magnitude compared to digital computing.
Hierarchical federated learning should be treated as an architecture-aware design framework for networked AI in which convergence depends on chosen hierarchy depth, layer-wise optimization roles, and communication realizations.
Proposes subcarrier selection to remove OFDM frequency redundancy in multi-device ISCC, with analytical models, ADMM optimization, and commodity device experiments showing gains over baselines.
A survey consolidating research on edge perception by examining sensing modalities, edge AI, their synergies, task-driven designs, and open challenges for 6G networks.
citing papers explorer
-
Distributed Perceptron under Bounded Staleness, Partial Participation, and Noisy Communication
Introduces staleness-bucket aggregation with padding for distributed perceptron and proves finite-horizon mistake bounds where delay affects only mean staleness and noise adds a sqrt(horizon) term.
-
Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems
Analog RF computing performs neural network matrix-vector multiplications via RF waveform mixing at clients in MU-MIMO systems, reducing energy consumption by nearly two orders of magnitude compared to digital computing.
-
Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design
Hierarchical federated learning should be treated as an architecture-aware design framework for networked AI in which convergence depends on chosen hierarchy depth, layer-wise optimization roles, and communication realizations.
-
Toward Efficient Sensing in Multi-Device ISCC by Removing Frequency Domain Redundancy
Proposes subcarrier selection to remove OFDM frequency redundancy in multi-device ISCC, with analytical models, ADMM optimization, and commodity device experiments showing gains over baselines.
-
Sense Smarter, Think Better: A Survey on Edge Perception for Next-Generation Networks
A survey consolidating research on edge perception by examining sensing modalities, edge AI, their synergies, task-driven designs, and open challenges for 6G networks.