CoChat
Sign Up
Cited by 337Ethics and Social Impacts of AIRecommender Systems and TechniquesInformation Retrieval and Search Behavior

Equity of Attention: Amortizing Individual Fairness in Rankings

Biega, Asia J., Gummadi, Krishna P., Weikum, Gerhard·2018·The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval
DOI 10.1145/3209978.3210063
Open this paper in CoChat — free account

Abstract

Rankings of people and items are at the heart of selection-making, match-making, and recommender systems, ranging from employment sites to sharing economy platforms. As ranking positions influence the amount of attention the ranked subjects receive, biases in rankings can lead to unfair distribution of opportunities and resources such as jobs or income. This paper proposes new measures and mechanisms to quantify and mitigate unfairness from a bias inherent to all rankings, namely, the position bias which leads to disproportionately less attention being paid to low-ranked subjects. Our approach differs from recent fair ranking approaches in two important ways. First, existing works measure unfairness at the level of subject groups while our measures capture unfairness at the level of individual subjects, and as such subsume group unfairness. Second, as no single ranking can achieve individual attention fairness, we propose a novel mechanism that achieves amortized fairness, where attention accumulated across a series of rankings is proportional to accumulated relevance. We formulate the challenge of achieving amortized individual fairness subject to constraints on ranking quality as an online optimization problem and show that it can be solved as an integer linear program. Our experimental evaluation reveals that unfair attention distribution in rankings can be substantial, and demonstrates that our method can improve individual fairness while retaining high ranking quality.

Integrity signals

Registry

Crossref · 10.1145/3209978.3210063

Cites

22 of 22 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The tendency to interact with top-positioned items without considering their relevance creates Position Bias.

    “This tendency to interact with top-positioned items without considering their relevance creates Position Bias [7, 78, 84, 85].”

    From A Deep Dive into Fairness, Bias, Threats, and Privacy in Recommender Systems: Insights and Future Research (2024) · cites this paper as [78]

  • Uncontrolled biases in recommender systems can lead to uneven distribution of opportunities and resources, exacerbating echo chamber or filter bubble effects.

    “Usually, a biased system generates the biased output, and the uncontrolled biases can lead to the uneven distribution of opportunities and resources [58, 78], exacerbating the “ 𝐸𝑐ℎ𝑜 𝐶ℎ𝑎𝑚𝑏𝑒𝑟 ” or “ 𝐹𝑖𝑙𝑡𝑒𝑟 𝐵𝑢𝑏𝑏𝑙𝑒𝑠 ” effects [86, 87].”

    From A Deep Dive into Fairness, Bias, Threats, and Privacy in Recommender Systems: Insights and Future Research (2024) · cites this paper as [78]

  • Users are more likely to interact with items at the top of the recommendation list because these items quickly capture attention.

    “Users are more likely to interact with items at the top of the recommendation list because these items quickly capture attention [78].”

    From A Deep Dive into Fairness, Bias, Threats, and Privacy in Recommender Systems: Insights and Future Research (2024) · cites this paper as [78]

  • Considerations of fairness have been actively studied in the context of rankings and recommender systems.

    “Considerations of fairness have been actively studied in the context of rankings and recommender systems.”

    From Fairness in machine learning: A survey (2024) · cites this paper as [32]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Biega, A. J., Gummadi, K. P., & Weikum, G.
Affiliations
  • Max Planck Institute for Informatics (DE)
  • Max Planck Institute for Software Systems (DE)
ORCID
Venue
The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval
Publisher
ACM
Published
2018-06-27
Pages
405-414
DOI
10.1145/3209978.3210063
OpenAlex
W4300482433
Cited by
337
References
22
Citations by year
2026: 42 · 2025: 42 · 2024: 64 · 2023: 40 · 2022: 52 · 2021: 50 · 2020: 21 · 2019: 22 · 2018: 3 · 2012: 1
FWCI
42.96
Type
conference paper
Language
en
Open access
closed
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion)
Funders
ERC Synergy Grant (610150)
Topics
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
Keywords
position bias, ranking fairness, individual fairness, recommender systems, online optimization, integer linear programming

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review