AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching

Ren Kishimoto, Rikiya Takehi, Koichi Tanaka, Yoji Tomita, Masahiro Nomura, Riku Togashi, Yuta Saito

ICLR 2026 · Learning theory and algorithms › Fairness · approach: Fairness in recommendation and ranking · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MRet instead of Max Matchranking · Synthetic matchinguser retention rateImproved
use MRet instead of FairCoranking · Synthetic matchinguser retention rateImproved
maximize matches (Max Match) instead of uniform random rankingranking · Synthetic matchinguser retention rateNo clear effect
increase popularity skew kappa for Max MatchMax Match · Synthetic matchinguser retention rateHurt
add fairness-of-exposure term (FairCo) to match maximizationranking · Synthetic matching, skewed popularityuser retention rateNo clear effect
use FairCo lambda=0.1 instead of default 100 (ablation)FairCo · Synthetic matchinguser retention rateImproved
use FairCo with equal-exposure criterion (ablation)FairCo · Synthetic matchinguser retention rateImproved
learn retention function with XGBoost instead of oracle f (MRet vs MRet best) (ablation)MRet · Synthetic matchinguser retention rateHurt
use MRet instead of fairness baselines on sparse real dating dataranking · Real dating platform datauser retention rateImproved
use FairCo/Uniform instead of Max Match on sparse real dataranking · Real dating platform datauser retention rateHurt
increase retention-model training data to n=16000 (ablation)MRet · Real dating platform datauser retention rateImproved
apply MRet when retention function is non-concaveMRet · Real dating platform datauser retention rateNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy