One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions

• URL: http://arxiv.org/abs/2308.16681v3
• Date: Wed, 19 Jun 2024 00:49:07 GMT
• Title: One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions
• Authors: Jan Simson, Florian Pfisterer, Christoph Kern,
• Abstract summary: We show how multiverse analysis can be used to better understand fairness implications of design and evaluation decisions. Our results highlight how decisions regarding the evaluation of a system can lead to vastly different fairness metrics for the same model.
• Score: 4.362723406385396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A vast number of systems across the world use algorithmic decision making (ADM) to (partially) automate decisions that have previously been made by humans. The downstream effects of ADM systems critically depend on the decisions made during a systems' design, implementation, and evaluation, as biases in data can be mitigated or reinforced along the modeling pipeline. Many of these decisions are made implicitly, without knowing exactly how they will influence the final system. To study this issue, we draw on insights from the field of psychology and introduce the method of multiverse analysis for algorithmic fairness. In our proposed method, we turn implicit decisions during design and evaluation into explicit ones and demonstrate their fairness implications. By combining decisions, we create a grid of all possible "universes" of decision combinations. For each of these universes, we compute metrics of fairness and performance. Using the resulting dataset, one can investigate the variability and robustness of fairness scores and see how and which decisions impact fairness. We demonstrate how multiverse analyses can be used to better understand fairness implications of design and evaluation decisions using an exemplary case study of predicting public health care coverage for vulnerable populations. Our results highlight how decisions regarding the evaluation of a system can lead to vastly different fairness metrics for the same model. This is problematic, as a nefarious actor could optimise or "hack" a fairness metric to portray a discriminating model as fair merely by changing how it is evaluated. We illustrate how a multiverse analysis can help to address this issue.

Related papers

• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making [29.071173441651734]
  We identify five sources of target variable bias that can impact the validity of proxy labels in human-AI decision-making tasks. We develop a causal framework to disentangle the relationship between each bias. We conclude by discussing opportunities to better address target variable bias in future research.
  arXiv  Detail & Related papers  (2023-02-13T16:29:11Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Towards Better Understanding Attribution Methods [77.1487219861185]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We also propose a post-processing smoothing step that significantly improves the performance of some attribution methods.
  arXiv  Detail & Related papers  (2022-05-20T20:50:17Z)
• Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies [79.60322329952453]
  We show how to develop interpretable representations of how agents make decisions. By understanding the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem. We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them. Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
  arXiv  Detail & Related papers  (2022-03-14T17:40:42Z)
• VisRuler: Visual Analytics for Extracting Decision Rules from Bagged and Boosted Decision Trees [3.5229503563299915]
  Bagging and boosting are two popular ensemble methods in machine learning (ML) that produce many individual decision trees. We propose a visual analytics tool that aims to assist users in extracting decisions from such ML models.
  arXiv  Detail & Related papers  (2021-12-01T08:01:02Z)
• On the Fairness of Machine-Assisted Human Decisions [3.4069627091757178]
  We show that the inclusion of a biased human decision-maker can revert common relationships between the structure of the algorithm and the qualities of resulting decisions. In the lab experiment, we demonstrate how predictions informed by gender-specific information can reduce average gender disparities in decisions.
  arXiv  Detail & Related papers  (2021-10-28T17:24:45Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)
• Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
  We present a general methodology for interpretable evaluation for the named entity recognition (NER) task. The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them. By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
  arXiv  Detail & Related papers  (2020-11-13T10:53:27Z)
• Morshed: Guiding Behavioral Decision-Makers towards Better Security Investment in Interdependent Systems [10.960507931439317]
  We model the behavioral biases of human decision-making in securing interdependent systems. We show that such behavioral decision-making leads to a suboptimal pattern of resource allocation. We propose three learning techniques for enhancing decision-making in multi-round setups.
  arXiv  Detail & Related papers  (2020-11-12T18:23:55Z)

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.