Fairness evaluation

Benchmarks

Dataset Name	SOTA Method	Metric
CrowS-Pairs	Self-Debias Iter2 + Self-Correction	Score72.2	16	1mo ago
CEB-Jigsaw	Self-Debias Iter1 + Self-Correction	Score73.5	16	1mo ago
CEB-Credit	Self-Debias Iter2	Score65.8	16	1mo ago
CEB Adult	Self-Debias Iter1	Score68.3	16	1mo ago
UnQover	Self-Debias Offline + Self-Correction	Score99.6	16	1mo ago
Dollar Street and GeoDE		Fairness Mean78.48	16	3mo ago
Credit card Sex	TabFairGan	Statistical Parity-0.0577	15	2mo ago
PPVR (test)	FairGBM	PP53.24	14	2mo ago
PPR (test)		PP4.26	14	2mo ago
Income (test)	POAF	PP0.95	14	2mo ago
Credit (test)		PP5.66	14	2mo ago
COMPAS	COFT	COMPAS Gap0.113	10	2d ago
Utrecht	COFT	Utrecht DP11.2	10	2d ago
Credit card Age	FairFinGAN-EOd	Statistical Parity-0.1679	10	2mo ago
Jigsaw	AWQ-trust	BiasAUC75.6	9	3mo ago
CrowS-Pair Fr		SS51.461	9	3mo ago
CrowS-Pair En		Stereotype Score65.057	9	3mo ago
EquityMedQA cross-population (test)	SAG	CDR (Race)0.8	8	3mo ago
Ricci (test)		PP1.82	7	2mo ago
BAF (test)		DPD (Disparate Impact Difference)3.91	6	1mo ago
BAF (train)	FCorrTransformer	DPD0.0456	6	1mo ago
EquityMedQA (test)	SAG	Race CDR4.9	6	3mo ago
Adult Dataset (test)	GPT-4	Accuracy76.54	6	2mo ago
Maritime Digital Twin 16 ports 50 vessels mean-over-episodes	EcoFair-CH-MARL (QMIX)	Gini Coefficient0	5	2mo ago
Dutch census Sex		Statistical Parity29.85	5	2mo ago

Showing 25 of 28 rows