Roman Rischke
YOU?
Author Swipe
View article: Federated Learning in Dentistry: Chances and Challenges
Federated Learning in Dentistry: Chances and Challenges Open
Building performant and robust artificial intelligence (AI)–based applications for dentistry requires large and high-quality data sets, which usually reside in distributed data silos from multiple sources (e.g., different clinical institut…
View article: FedAUXfdp: Differentially Private One-Shot Federated Distillation
FedAUXfdp: Differentially Private One-Shot Federated Distillation Open
Federated learning suffers in the case of non-iid local datasets, i.e., when the distributions of the clients' data are heterogeneous. One promising approach to this challenge is the recently proposed method FedAUX, an augmentation of fede…
View article: FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning
FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning Open
Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning, which achieves training performance competitive to prior parameter averaging based methods, while additionally allowing the clients to train differ…
View article: CFD: Communication-Efficient Federated Distillation via Soft-Label Quantization and Delta Coding
CFD: Communication-Efficient Federated Distillation via Soft-Label Quantization and Delta Coding Open
Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally differ…
View article: Optimal algorithms for scheduling under time-of-use tariffs
Optimal algorithms for scheduling under time-of-use tariffs Open
We consider a natural generalization of classical scheduling problems to a setting in which using a time unit for processing a job causes some time-dependent cost, the time-of-use tariff, which must be paid in addition to the standard sche…
View article: Communication-Efficient Federated Distillation
Communication-Efficient Federated Distillation Open
Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally differ…
View article: Optimal Algorithms for Scheduling under Time-of-Use Tariffs
Optimal Algorithms for Scheduling under Time-of-Use Tariffs Open
We consider a natural generalization of classical scheduling problems in which using a time unit for processing a job causes some time-dependent cost which must be paid in addition to the standard scheduling cost. We study the scheduling o…
View article: Deterministic, Stochastic, and Robust Cost-Aware Scheduling
Deterministic, Stochastic, and Robust Cost-Aware Scheduling Open
Scheduling concerns the temporal allocation of tasks to scarce resources with the objective of optimizing some performance measure subject to certain side constraints. Classical scheduling problems do not address the fact that in practice …