Searcharxiv⌕ Search

arXiv subjects

Claudio Geyer

Publications and source records attributed to Claudio Geyer.

3 recordsLinked to original sources

Performance Benchmarking of Federated Learning Frameworks for Medical Image Classification

Selecting a Federated Learning (FL) framework requires understanding the resource demands of its training and evaluation workflow. This work compares Flower, NVIDIA FLARE, and FedBioMed using two-dimensional MedNIST classification with ResNet-10 in a containerized, single-host environment. Following a dated review of repository activity and documented medical applications, we evaluated nine configurations per framework, with three random seeds, for a total of 81 executions. The configurations varied federation size, communication rounds, and batch size. We monitored execution time, CPU and RAM consumption, host-level GPU utilization, server network traffic rates, and model accuracy at the end of each execution. The implementations shared nominal learning settings while retaining differences in data splitting and federated evaluation. Configuration-blocked non-parametric analysis identified differences in execution time, client and server memory, GPU utilization, and network traffic rates. NVIDIA FLARE exhibited the lowest server-memory consumption and the highest host-level GPU utilization, Flower exhibited the highest average server network traffic rate, and FedBioMed required more client memory and longer execution time. No statistically significant difference in final accuracy was detected within the evaluated short training schedules; this does not establish convergence or equivalent predictive performance. The results characterize the configured workflows under shared hardware resources. They provide a concrete case study of system behavior, with conclusions bounded by workflow asymmetries, local networking, and the lightweight MedNIST workload.

cs.DC↗

A Lifecycle Cost Analysis of Smart-Contract-Coordinated Federated Learning Marketplaces

Blockchain-enabled Federated Learning (FL) marketplaces enable collaborative model training among mutually distrustful participants through smart contracts. Although numerous architectures exist, their economic evaluation is typically limited to isolated blockchain operations rather than the complete marketplace lifecycle. Consequently, it remains unclear whether operational costs depend on operating at scale. This paper presents an experimental study of the operational cost of a DAO-governed marketplace. Our evaluation decomposes the gas consumption of every blockchain operation throughout the contract lifecycle, performs ablation experiments to isolate the impact of on-chain coordination and IPFS storage on federated training, and derives an analytical model describing the amortization of deployment costs. Results show the lifecycle of a single training task consumes approximately 3.8 million gas units per hired trainer. The average cost per training round reaches its amortization knee - defined as twice the asymptotic recurring cost - after approximately 20 communication rounds. Moreover, integrating smart contracts and IPFS preserves model performance, achieving accuracy comparable to conventional FL deployments. These findings demonstrate that smart-contract-coordinated FL marketplaces exhibit an amortizing cost structure not because on-chain operations are inexpensive, but because recurring costs are one to two orders of magnitude smaller than fixed deployment costs, thereby diluting over the federation's lifetime.

cs.DC↗

Strategies for Big Data Analytics through Lambda Architectures in Volatile Environments

Expectations regarding the future growth of Internet of Things (IoT)-related technologies are high. These expectations require the realization of a sustainable general purpose application framework that is capable to handle these kinds of environments with their complexity in terms of heterogeneity and volatility. The paradigm of the Lambda architecture features key characteristics (such as robustness, fault tolerance, scalability, generalization, extensibility, ad-hoc queries, minimal maintenance, and low-latency reads and updates) to cope with this complexity. The paper at hand suggest a basic set of strategies to handle the arising challenges regarding the volatility, heterogeneity, and desired low latency execution by reducing the overall system timing (scheduling, execution, monitoring, and faults recovery) as well as possible faults (churn, no answers to executions). The proposed strategies make use of services such as migration, replication, MapReduce simulation, and combined processing methods (batch- and streaming-based). Via these services, a distribution of tasks for the best balance of computational resources is achieved, while monitoring and management can be performed asynchronously in the background. %An application of batch and stream-based methods are proposed to reduce the latency.

cs.DC↗