For decentralized secure aggregation with at least U surviving users and at most T colluders, the optimal two-round rates are R1 ≥ 1 and R2 ≥ 1/(U-T-1) when U > T+1, and the task is impossible otherwise.
Communication-Efficient Learning of Deep Networks from Decentralized Data
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Routing optimization for in-orbit federated learning is polynomial-time solvable under some settings like certain unicast or multicast flows and NP-hard under others, with rigorous proofs establishing the boundaries.
TiLP integrates network, training, and task sub-twins into a digital twin and uses receding-horizon cross-entropy planning with actor-critic guidance to jointly optimize resource allocation in federated split learning, improving task success by 9.5 percentage points on robotic tasks.
Asynchronous probability ensembling allows heterogeneous CNNs to collaborate in federated disaster detection by exchanging class probabilities instead of weights, reducing communication and improving accuracy.
FLARE uses adaptive multi-dimensional reputation scores and soft exclusion to improve Byzantine robustness in federated learning by up to 16% over prior methods while handling a new Statistical Mimicry attack.
EnCAgg filters malicious gradients in federated learning by projecting updates to two divergent dimensions for density clustering, generating boundary pseudo-gradients to link outliers, and re-clustering to recover benign updates even with unknown variable attackers.
citing papers explorer
-
Information-Theoretic Decentralized Secure Aggregation with User Dropouts
For decentralized secure aggregation with at least U surviving users and at most T colluders, the optimal two-round rates are R1 ≥ 1 and R2 ≥ 1/(U-T-1) when U > T+1, and the task is impossible otherwise.
-
Optimal Routing for Federated Learning over Dynamic Satellite Networks: Tractable or Not?
Routing optimization for in-orbit federated learning is polynomial-time solvable under some settings like certain unicast or multicast flows and NP-hard under others, with rigorous proofs establishing the boundaries.
-
Application-Aware Twin-in-the-Loop Planning for Federated Split Learning over Wireless Edge Networks
TiLP integrates network, training, and task sub-twins into a digital twin and uses receding-horizon cross-entropy planning with actor-critic guidance to jointly optimize resource allocation in federated split learning, improving task success by 9.5 percentage points on robotic tasks.
-
Asynchronous Probability Ensembling for Federated Disaster Detection
Asynchronous probability ensembling allows heterogeneous CNNs to collaborate in federated disaster detection by exchanging class probabilities instead of weights, reducing communication and improving accuracy.
-
FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
FLARE uses adaptive multi-dimensional reputation scores and soft exclusion to improve Byzantine robustness in federated learning by up to 16% over prior methods while handling a new Statistical Mimicry attack.
-
EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
EnCAgg filters malicious gradients in federated learning by projecting updates to two divergent dimensions for density clustering, generating boundary pseudo-gradients to link outliers, and re-clustering to recover benign updates even with unknown variable attackers.