Search Results for author:
Found 4 papers, 2 papers with code
Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning
In practice, there can often be substantial heterogeneity (e. g., class imbalance) across the local data distributions observed by each of these clients.
ElfStore: A Resilient Data Storage Service for Federated Edge and Fog Resources
Edges host the actual data blocks, and we use a unique differential replication scheme to select edges on which to replicate blocks, to guarantee a minimum reliability and to balance storage utilization.
Distributed, Parallel, and Cluster Computing
ECHO: An Adaptive Orchestration Platform for Hybrid Dataflows across Cloud and Edge
ECHO can schedule the dataflow on different Edge, Fog and Cloud resources, and also perform dynamic task migration between resources.
Distributed, Parallel, and Cluster Computing
Holistic Measures for Evaluating Prediction Models in Smart Grids
The performance of prediction models is often based on "abstract metrics" that estimate the model's ability to limit residual errors between the observed and predicted values.
