Federated Nearest Neighbor Classification with a Colony of Fruit-Flies

Authors

  • Parikshit Ram IBM Research
  • Kaushik Sinha Wichita State University, NSF AI Institute for Foundations of Machine Learning

DOI:

https://doi.org/10.1609/aaai.v36i7.20775

Keywords:

Machine Learning (ML)

Abstract

The mathematical formalization of a neurological mechanism in the fruit-fly olfactory circuit as a locality sensitive hash (Flyhash) and bloom filter (FBF) has been recently proposed and "reprogrammed" for various learning tasks such as similarity search, outlier detection and text embeddings. We propose a novel reprogramming of this hash and bloom filter to emulate the canonical nearest neighbor classifier (NNC) in the challenging Federated Learning (FL) setup where training and test data are spread across parties and no data can leave their respective parties. Specifically, we utilize Flyhash and FBF to create the FlyNN classifier, and theoretically establish conditions where FlyNN matches NNC. We show how FlyNN is trained exactly in a FL setup with low communication overhead to produce FlyNNFL, and how it can be differentially private. Empirically, we demonstrate that (i) FlyNN matches NNC accuracy across 70 OpenML datasets, (ii) FlyNNFL training is highly scalable with low communication overhead, providing up to 8x speedup with 16 parties.

Downloads

Published

2022-06-28

How to Cite

Ram, P., & Sinha, K. (2022). Federated Nearest Neighbor Classification with a Colony of Fruit-Flies. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 8036-8044. https://doi.org/10.1609/aaai.v36i7.20775

Issue

Section

AAAI Technical Track on Machine Learning II