Function Comparison of Different Federated Learning Schemes

Jie Guo published a dataset on 2026-05-18 comparing optimized federated learning schemes. The dataset likely contains performance metrics for schemes integrating adaptive channel pruning with multi-key homomorphic encryption. It was tested on MNIST and CIFAR-10 datasets to evaluate communication overhead and privacy.

Use Cases

• Benchmarking communication efficiency based on the described adaptive pruning mechanism.
• Evaluating privacy guarantees against collusion attacks based on the multi-key BGV encryption architecture.
• Comparing model accuracy trade-offs under different compression rates mentioned in the dynamic threshold mechanism.

Strengths

• Dataset is published under the CC-BY-4.0 license, allowing for open sharing and modification.
• The underlying research was validated on standard benchmark datasets MNIST and CIFAR-10.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

Jie Guo via figshare

Collection Method

Likely contains experimental results from comparing federated learning schemes.

Freshness

Last updated 2026-05-18 17:41:59; freshness should be verified.