MétaCan
Menu
Back to cohort
Record W3092787839

Exchanging Lessons Between Algorithmic Fairness and Domain Generalization

2021· preprint· en· W3092787839 on OpenAlexaff
Elliot Creager, Joern-Henrik Jacobsen, Richard S. Zemel

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsVector InstituteUniversity of Toronto
Fundersnot available
KeywordsGeneralizationComputer scienceDisjoint setsTask (project management)Machine learningArtificial intelligenceDomain (mathematical analysis)Theoretical computer scienceMathematics
DOInot available

Abstract

fetched live from OpenAlex

Standard learning approaches are designed to perform well on average for the data distribution available at training time. Developing learning approaches that are not overly to the training distribution is central to research on domain- or out-of-distribution generalization, robust optimization and fairness. In this work we focus on links between research on domain generalization and algorithmic fairness---where performance under a distinct but related test distributions is studied---and show how the two fields can be mutually beneficial. While domain generalization methods typically rely on knowledge of disjoint domains or environments, sensitive label information indicating which demographic groups are at risk of discrimination is often used in the fairness literature. Drawing inspiration from recent fairness approaches that improve worst-case performance without knowledge of groups, we propose a novel domain generalization method that handles the more realistic scenario where environment partitions are not provided. We then show theoretically and empirically how different partitioning schemes can lead to increased or decreased generalization performance, enabling us to outperform Invariant Risk Minimization with handcrafted environments in multiple cases. We also show how a re-interpretation of IRMv1 allows us for the first time to directly optimize a common fairness criterion, group-sufficiency, and thereby improve performance on a fair prediction task.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.020
metaresearch head score (Gemma)0.084
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.020
Threshold uncertainty score0.106

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0200.084
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0020.006
Scholarly communication0.0030.008
Open science0.0030.007
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.089
GPT teacher head0.209
Teacher spread0.120 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations9
Published2021
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207