Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fair Learning for Bias Mitigation and Quality Optimization in Paper Recommendation

Uttamasha Anjally Oyshi, Susan Gauch

TL;DR

Evaluations indicate that diversity promotion does not compromise academic rigor and supports equity-focused peer review solutions, indicating that diversity promotion does not compromise academic rigor and supports equity-focused peer review solutions.

Abstract

Despite frequent double-blind review, demographic biases of authors still disadvantage the underrepresented groups. We present Fair-PaperRec, a MultiLayer Perceptron (MLP)-based model that addresses demographic disparities in post-review paper acceptance decisions while maintaining high-quality requirements. Our methodology penalizes demographic disparities while preserving quality through intersectional criteria (e.g., race, country) and a customized fairness loss, in contrast to heuristic approaches. Evaluations using conference data from ACM Special Interest Group on Computer-Human Interaction (SIGCHI), Designing Interactive Systems (DIS), and Intelligent User Interfaces (IUI) indicate a 42.03% increase in underrepresented group participation and a 3.16% improvement in overall utility, indicating that diversity promotion does not compromise academic rigor and supports equity-focused peer review solutions.

Fair Learning for Bias Mitigation and Quality Optimization in Paper Recommendation

TL;DR

Evaluations indicate that diversity promotion does not compromise academic rigor and supports equity-focused peer review solutions, indicating that diversity promotion does not compromise academic rigor and supports equity-focused peer review solutions.

Abstract

Despite frequent double-blind review, demographic biases of authors still disadvantage the underrepresented groups. We present Fair-PaperRec, a MultiLayer Perceptron (MLP)-based model that addresses demographic disparities in post-review paper acceptance decisions while maintaining high-quality requirements. Our methodology penalizes demographic disparities while preserving quality through intersectional criteria (e.g., race, country) and a customized fairness loss, in contrast to heuristic approaches. Evaluations using conference data from ACM Special Interest Group on Computer-Human Interaction (SIGCHI), Designing Interactive Systems (DIS), and Intelligent User Interfaces (IUI) indicate a 42.03% increase in underrepresented group participation and a 3.16% improvement in overall utility, indicating that diversity promotion does not compromise academic rigor and supports equity-focused peer review solutions.
Paper Structure (29 sections, 9 equations, 7 figures, 4 tables, 2 algorithms)

This paper contains 29 sections, 9 equations, 7 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Double-Blind Review and Bias in Academic Paper Selection
  4. Fairness in Recommendation Systems
  5. Post-Review Bias Mitigation and Neural Approaches
  6. Methodology
  7. Data Collection and Pre-processing
  8. Data Description
  9. Data Pre-processing
  10. Problem Definition
  11. Demographic Parity
  12. Fairness Loss
  13. Combined Fairness Loss
  14. Total Loss
  15. Constraints and Considerations
  16. ...and 14 more sections

Figures (7)

  • Figure 1: Overview of the Fair-PaperRec Architecture.
  • Figure 2: Comparison of Macro and Micro Gains for Country Across Different Fairness Configurations.
  • Figure 3: Comparison of Macro and Micro Gains for Race Across Different Fairness Configurations.
  • Figure : (a) Utility Gain.
  • Figure : (a) Utility Gain.
  • ...and 2 more figures