Spiking neural networks have attracted increasing attention in recent years due to their potential of handling time-dependent data.

Intrinsic evaluations focus on the inherent properties of the model, while extrinsic evaluations measure biases in the context of specific tasks.

Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to learn collaboratively without sharing their private data. However, excessivecomputation and communication demands pose challenges to current FL frameworks, especially when training large-scale models.

Lloyd's algorithm uses iterative improvements to find a locally optimalk-means clustering. The performance of Lloyd'salgorithm crucially depends on the quality of the initial clustering, which isdefined bytheinitial setofcenters, called aseed.

T result, wegicover(see Arthur and Vassilvitskii(2007) and Lemma4.1 inthispaper).