System-level Profiling: MNIST / 2NN / C=10 / 10 Mbps Uplink

5.5 KB of system-level profiling data for a federated learning experiment, shared by Jie Guo on figshare. The dataset, last updated on 2026-05-18, is stored in an XLS file. It likely contains performance metrics from a simulation using the MNIST dataset and a 2-layer neural network.

Use Cases

• Benchmarking federated learning system performance based on the described simulation setup
• Analyzing the impact of a 10 Mbps uplink constraint on training efficiency
• Profiling resource usage for a 2-layer neural network (2NN) on MNIST
• Comparing communication or computation overhead across different federated learning configurations

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• The description provides specific simulation parameters (MNIST, 2NN, C=10, 10 Mbps uplink).
• It is shared under a permissive CC-BY-4.0 license.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is limited to the title; actual data quality requires manual inspection.

Provenance

Source

figshare, author Jie Guo

Collection Method

Likely generated from a federated learning simulation.

Freshness

Last updated 2026-05-18 17:42:04