REVIEW 2 cited by
Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Federated Kolmogorov-Arnold Networks (F-KANs) have already been proposed, but their assessment is at an initial stage. We present a comparison between KANs (using B-splines and Radial Basis Functions as activation functions) and Multi- Layer Perceptrons (MLPs) with a similar number of parameters for 100 rounds of federated learning in the MNIST classification task using non-IID partitions with 100 clients. After 15 trials for each model, we show that the best accuracies achieved by MLPs can be achieved by Spline-KANs in half of the time (in rounds), with just a moderate increase in computing time.
Forward citations
Cited by 2 Pith papers
-
Concurrent training methods for Kolmogorov-Arnold networks: Disjoint datasets and FPGA implementation
Three concurrency tricks — group-wise pre-training, disjoint-batch training with parameter averaging, and fixed-point FPGA execution — speed up Newton-Kaczmarz KAN training, with measured CPU gains of ~7-9x over the a...
-
Enhancing Federated Learning with Kolmogorov-Arnold Networks: A Comparative Study Across Diverse Aggregation Strategies
KANs achieve higher or comparable accuracy to MLPs across four tabular datasets in simulated federated learning, using fewer communication rounds.
Discussion (0). Continue with ORCID to comment.