FairFuse: Interactive Visual Support for Fair Consensus Ranking

Hilson, Shrestha,; Cachel, Kathleen; Alkhathlan, Mallak; Rundensteiner, Elke A.; Harrison, Lane

doi:10.1109/vis54862.2022.00022

Cited by 2 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To be able to study the challenges and opportunities in visualizing fairness metrics and algorithms, we have modified the FairFuse system [48] to create two system variations. The FairFuse system employed task abstraction methodologies following procedures from Lam et al [31] and recent works on group decision-making by Hindalong et al [23,24].…”

Section: Visualization and Interaction Designmentioning

confidence: 99%

“…The limitations of FairFuse [48] are also relevant to this crowdsourced study. FairFuse focusses on ARP and FPR fairness metrics [10] within the widely accepted definition of group fairness in the fairness community.…”

Section: Limitations and Future Workmentioning

confidence: 99%

“…treating all groups in the ranking similarly, e.g. [1,10,30,48,57]. We begin with a recently published fairness visualization with an available open source system, Fair-Fuse [48], which visualizes both the candidate items to be ranked and various fairness metrics such as Favored Pair Representation (FPR), Attribute Rank Parity (ARP), and PD Loss [10].…”

Section: Introductionmentioning

confidence: 99%

“…[1,10,30,48,57]. We begin with a recently published fairness visualization with an available open source system, Fair-Fuse [48], which visualizes both the candidate items to be ranked and various fairness metrics such as Favored Pair Representation (FPR), Attribute Rank Parity (ARP), and PD Loss [10]. We adapt FairFuse into a new system, ConsensusFuse, by removing visualized We compare two systems: A: ConsensusFuse, a visualization that enables fairness comparison only by interactive visual displays of underlying items.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Help or Hinder? Evaluating the Impact of Fairness Metrics and Algorithms in Visualizations for Consensus Ranking

Hilson

Cachel

Alkhathlan

et al. 2023

2023 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

For applications where multiple stakeholders provide recommendations, a fair consensus ranking must not only ensure that the preferences of rankers are well represented, but must also mitigate disadvantages among socio-demographic groups in the final result. However, there is little empirical guidance on the value or challenges of visualizing and integrating fairness metrics and algorithms into human-in-the-loop systems to aid decision-makers. In this work, we design a study to analyze the effectiveness of integrating such fairness metrics-based visualization and algorithms. We explore this through a task-based crowdsourced experiment comparing an interactive visualization system for constructing consensus rankings, ConsensusFuse, with a similar system that includes visual encodings of fairness metrics and fair-rank generation algorithms, FairFuse. We analyze the measure of fairness, agreement of rankers' decisions, and user interactions in constructing the fair consensus ranking across these two systems. In our study with 200 participants, results suggest that providing these fairness-oriented support features nudges users to align their decision with the fairness metrics while minimizing the tedious process of manually having to amend the consensus ranking. We discuss the implications of these results for the design of next-generation fairness oriented-systems and along with emerging directions for future research.

show abstract

Section: Visualization and Interaction Designmentioning

confidence: 99%

Section: Limitations and Future Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Help or Hinder? Evaluating the Impact of Fairness Metrics and Algorithms in Visualizations for Consensus Ranking

Hilson

Cachel

Alkhathlan

et al. 2023

2023 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

show abstract

“…Furthermore, the dissection of fairness narratives, especially within microlending and educational systems, underscores the need to take into account diversified stakeholder perspectives [124], [125]. Benbouzid et al [126] and Shrestha et al [127] enunciate the importance of optimizing AI to embrace scientific fairness and effective collective decision making.…”

Section: Algorithmic Fairnessmentioning

confidence: 99%

Classification of Kinematic Data Using Explainable Artificial Intelligence (XAI) for Smart Motion

Yong¹

2021

Explainable Artificial Intelligence for Smart Cities

View full text Add to dashboard Cite

Given the complexity and lack of transparency in deep neural networks (DNNs), extensive efforts have been made to make these systems more interpretable or explain their behaviors in accessible terms. Unlike most reviews, which focus on algorithmic and model-centric perspectives, this work takes a "data-centric" view, examining how data collection, processing, and analysis contribute to explainable AI (XAI). We categorize existing work into three categories subject to their purposes: interpretations of deep models, referring to feature attributions and reasoning processes that correlate data points with model outputs; influences of training data, examining the impact of training data nuances, such as data valuation and sample anomalies, on decision-making processes; and insights of domain knowledge, discovering latent patterns and fostering new knowledge from data and models to advance social values and scientific discovery. Specifically, we distill XAI methodologies into data mining operations on training and testing data across modalities, such as images, text, and tabular data, as well as on training logs, checkpoints, models and other DNN behavior descriptors. In this way, our study offers a comprehensive, data-centric examination of XAI from a lens of data mining methods and applications.

show abstract

FairFuse: Interactive Visual Support for Fair Consensus Ranking

Cited by 2 publications

References 39 publications

Help or Hinder? Evaluating the Impact of Fairness Metrics and Algorithms in Visualizations for Consensus Ranking

Help or Hinder? Evaluating the Impact of Fairness Metrics and Algorithms in Visualizations for Consensus Ranking

Classification of Kinematic Data Using Explainable Artificial Intelligence (XAI) for Smart Motion

Contact Info

Product

Resources

About