Towards causally linking architectural parametrizations to algorithmic bias in neural networks

02/07/2023
by   Hao Liang, et al.
0

Training dataset biases are by far the most scrutinized factors when explaining algorithmic biases of neural networks. In contrast, hyperparameters related to the neural network architecture, e.g., the number of layers or choice of activation functions, have largely been ignored even though different network parameterizations are known to induce different implicit biases over learned features. For example, convolutional kernel size has been shown to bias CNNs towards different frequencies. In order to study the effect of these hyperparameters, we designed a causal framework for linking an architectural hyperparameter to algorithmic bias. Our framework is experimental, in that several versions of a network are trained with an intervention to a specific hyperparameter, and the resulting causal effect of this choice on performance bias is measured. We focused on the causal relationship between sensitivity to high-frequency image details and face analysis classification performance across different subpopulations (race/gender). In this work, we show that modifying a CNN hyperparameter (convolutional kernel size), even in one layer of a CNN, will not only change a fundamental characteristic of the learned features (frequency content) but that this change can vary significantly across data subgroups (race/gender populations) leading to biased generalization performance even in the presence of a balanced dataset.

READ FULL TEXT

page 6

page 7

page 10

page 11

page 20

page 21

page 22

page 23

research
07/02/2019

Quantifying Algorithmic Biases over Time

Algorithms now permeate multiple aspects of human lives and multiple rec...
research
09/15/2023

Biased Attention: Do Vision Transformers Amplify Gender Bias More than Convolutional Neural Networks?

Deep neural networks used in computer vision have been shown to exhibit ...
research
07/13/2020

Towards causal benchmarking of bias in face analysis algorithms

Measuring algorithmic bias is crucial both to assess algorithmic fairnes...
research
02/15/2023

On the Hyperparameters influencing a PINN's generalization beyond the training domain

Physics-Informed Neural Networks (PINNs) are Neural Network architecture...
research
10/03/2022

Convolutional networks inherit frequency sensitivity from image statistics

It is widely acknowledged that trained convolutional neural networks (CN...
research
04/28/2022

Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers

Convolutional Neural Networks (CNNs) are one of the most studied family ...
research
06/01/2023

Initial Guessing Bias: How Untrained Networks Favor Some Classes

The initial state of neural networks plays a central role in conditionin...

Please sign up or login with your details

Forgot password? Click here to reset