Model Selection's Disparate Impact in Real-World Deep Learning Applications

• URL: http://arxiv.org/abs/2104.00606v1
• Date: Thu, 1 Apr 2021 16:37:01 GMT
• Title: Model Selection's Disparate Impact in Real-World Deep Learning Applications
• Authors: Jessica Zosa Forde, A. Feder Cooper, Kweku Kwegyir-Aggrey, Chris De Sa and Michael Littman
• Abstract summary: Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. We contend that one source of such bias, human preferences in model selection, remains under-explored in terms of its role in disparate impact across demographic groups.
• Score: 3.924854655504237
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Algorithmic fairness has emphasized the role of biased data in automated decision outcomes. Recently, there has been a shift in attention to sources of bias that implicate fairness in other stages in the ML pipeline. We contend that one source of such bias, human preferences in model selection, remains under-explored in terms of its role in disparate impact across demographic groups. Using a deep learning model trained on real-world medical imaging data, we verify our claim empirically and argue that choice of metric for model comparison can significantly bias model selection outcomes.

Related papers

• FairGridSearch: A Framework to Compare Fairness-Enhancing Models [0.0]
  This paper focuses on binary classification and proposes FairGridSearch, a novel framework for comparing fairness-enhancing models. The study applies FairGridSearch to three popular datasets (Adult, COMPAS, and German Credit) and analyzes the impacts of metric selection, base estimator choice, and classification threshold on model fairness.
  arXiv  Detail & Related papers  (2024-01-04T10:29:02Z)
• Improving Bias Mitigation through Bias Experts in Natural Language Understanding [10.363406065066538]
  We propose a new debiasing framework that introduces binary classifiers between the auxiliary model and the main model. Our proposed strategy improves the bias identification ability of the auxiliary model.
  arXiv  Detail & Related papers  (2023-12-06T16:15:00Z)
• Bias in Evaluation Processes: An Optimization-Based Model [31.790546767744917]
  We model an evaluation process as a transformation of a distribution of the true utility of an individual for a task to an observed distribution. We characterize the distributions that arise from our model and study the effect of the parameters on the observed distribution. We empirically validate our model by fitting real-world datasets and use it to study the effect of interventions in a downstream selection task.
  arXiv  Detail & Related papers  (2023-10-26T15:45:01Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Subjectivity in Unsupervised Machine Learning Model Selection [2.9370710299422598]
  This study uses the Hidden Markov Model as an example to investigate the subjectivity involved in model selection. Sources of subjectivity include differing opinions on the importance of different criteria and metrics, differing views on how parsimonious a model should be, and how the size of a dataset should influence model selection.
  arXiv  Detail & Related papers  (2023-09-01T01:40:58Z)
• Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
  We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm. We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift. We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
  arXiv  Detail & Related papers  (2023-03-30T17:30:42Z)
• In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation [92.51773744318119]
  This paper empirically investigates the strengths and weaknesses of different model selection criteria. We highlight that there is a complex interplay between selection strategies, candidate estimators and the data used for comparing them.
  arXiv  Detail & Related papers  (2023-02-06T16:55:37Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization [77.8735802150511]
  We propose a cross-sample adversarial debiasing (CSAD) method to remove the bias information misused by the target task. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T21:17:02Z)
• Characterizing Fairness Over the Set of Good Models Under Selective Labels [69.64662540443162]
  We develop a framework for characterizing predictive fairness properties over the set of models that deliver similar overall performance. We provide tractable algorithms to compute the range of attainable group-level predictive disparities. We extend our framework to address the empirically relevant challenge of selectively labelled data.
  arXiv  Detail & Related papers  (2021-01-02T02:11:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.