Vectorization of Bias in Machine Learning Algorithms

Sophie Bekerman, Eric Chen, Lily Lin, George Monta Nez

2022

Abstract

We develop a method to measure and compare the inductive bias of classifications algorithms by vectorizing aspects of their behavior. We compute a vectorized representation of the algorithm’s bias, known as the inductive orientation vector, for a set of algorithms. This vector captures the algorithm’s probability distribution over all possible hypotheses for a classification task. We cluster and plot the algorithms’ inductive orientation vectors to visually characterize their relationships. As algorithm behavior is influenced by the training dataset, we construct a Benchmark Data Suite (BDS) matrix that considers algorithms’ pairwise distances across many datasets, allowing for more robust comparisons. We identify many relationships supported by existing literature, such as those between k-Nearest Neighbor and Random Forests and among tree-based algorithms, and evaluate the strength of those known connections, showing the potential of this geometric approach to investigate black-box machine learning algorithms.

Paper Citation

in Harvard Style

Bekerman S., Chen E., Lin L. and Monta Nez G. (2022). Vectorization of Bias in Machine Learning Algorithms. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 354-365. DOI: 10.5220/0010845000003116

in Bibtex Style

@conference{icaart22,
author={Sophie Bekerman and Eric Chen and Lily Lin and George Monta Nez},
title={Vectorization of Bias in Machine Learning Algorithms},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={354-365},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010845000003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Vectorization of Bias in Machine Learning Algorithms
SN - 978-989-758-547-0
AU - Bekerman S.
AU - Chen E.
AU - Lin L.
AU - Monta Nez G.
PY - 2022
SP - 354
EP - 365
DO - 10.5220/0010845000003116