LGAIOct 11, 2024

Evaluating Federated Kolmogorov-Arnold Networks on Non-IID Data

arXiv:2410.08961v16 citationsh-index: 2Has CodeLatinX in AI at Neural Information Processing Systems Conference 2024
Originality Synthesis-oriented
AI Analysis

This work provides an incremental evaluation for researchers in federated learning, comparing F-KANs to MLPs on non-IID data.

The paper tackled the problem of evaluating Federated Kolmogorov-Arnold Networks (F-KANs) on non-IID data in federated learning, showing that Spline-KANs achieved the same best accuracies as MLPs in half the number of rounds, with a moderate increase in computing time.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes