Modeling and Simultaneously Removing Bias via Adversarial Neural Networks

04/18/2018
by   John Moore, et al.
0

In real world systems, the predictions of deployed Machine Learned models affect the training data available to build subsequent models. This introduces a bias in the training data that needs to be addressed. Existing solutions to this problem attempt to resolve the problem by either casting this in the reinforcement learning framework or by quantifying the bias and re-weighting the loss functions. In this work, we develop a novel Adversarial Neural Network (ANN) model, an alternative approach which creates a representation of the data that is invariant to the bias. We take the Paid Search auction as our working example and ad display position features as the confounding features for this setting. We show the success of this approach empirically on both synthetic data as well as real world paid search auction data from a major search engine.

READ FULL TEXT
research
06/13/2023

Survey on Sociodemographic Bias in Natural Language Processing

Deep neural networks often learn unintended biases during training, whic...
research
10/08/2019

Bias-Resilient Neural Network

Presence of bias and confounding effects is inarguably one of the most c...
research
11/19/2020

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks

Collider bias is a harmful form of sample selection bias that neural net...
research
05/14/2020

Mitigating Gender Bias in Machine Learning Data Sets

Algorithmic bias has the capacity to amplify and perpetuatesocietal bias...
research
01/07/2021

Incorporating Vision Bias into Click Models for Image-oriented Search Engine

Most typical click models assume that the probability of a document to b...
research
07/08/2020

Unbiased Lift-based Bidding System

Conventional bidding strategies for online display ad auction heavily re...
research
08/22/2018

Clustering and Labelling Auction Fraud Data

Although shill bidding is a common auction fraud, it is however very tou...

Please sign up or login with your details

Forgot password? Click here to reset