Experimental Setup for Federated Learning with Adaptive Pruning and Multi-Key Encryption

Jie Guo's experimental results, shared on figshare in May 2026, describe an optimized federated learning scheme. The 5.5 KB XLS file likely contains tabular data comparing the performance of the proposed method against traditional algorithms. The scheme integrates adaptive channel pruning and multi-key homomorphic encryption to reduce communication overhead and resist collusion attacks.

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 protocol.
• Analyzing the trade-off between model accuracy and compression based on the dynamic threshold determination mechanism.

Strengths

• File size is precisely 5.5 KB, indicating a small, focused dataset.
• The description provides a detailed technical methodology for the proposed federated learning scheme.
• License is clearly specified as CC-BY-4.0, allowing for open reuse.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), suggesting limited scope, likely containing summary results rather than raw training data.

Provenance

Source

figshare

Collection Method

Likely contains experimental results from tests on MNIST and CIFAR-10 datasets as described.

Freshness

Last updated 2026-05-18 17:41:57; freshness should be verified.