Random Network Distillation enables pre-training discovery of client clusters in federated learning via local novelty signals, supporting autonomous grouping under non-IID data without a priori cluster count.
Filip Hanzely and Peter Richtárik
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
SP-CACW is a convergence-aware client weighting scheme for selfish personalized federated learning that minimizes an upper bound on the target client's convergence error and can zero out harmful peers.
C2FL proposes spatial clustering plus continual learning techniques inside federated learning to maintain performance under combined spatial heterogeneity and temporal drift.
citing papers explorer
-
Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning
Random Network Distillation enables pre-training discovery of client clusters in federated learning via local novelty signals, supporting autonomous grouping under non-IID data without a priori cluster count.
-
SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning
SP-CACW is a convergence-aware client weighting scheme for selfish personalized federated learning that minimizes an upper bound on the target client's convergence error and can zero out harmful peers.
-
C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift
C2FL proposes spatial clustering plus continual learning techniques inside federated learning to maintain performance under combined spatial heterogeneity and temporal drift.