Artificial Intelligence › Core AI ›

Fairness

1139 directly classified papers

Papers per year

Papers

Understanding and Mitigating Annotation Bias in Facial Expression Recognition ICCV 2021

Discover the Unknown Biased Attribute of an Image Classifier ICCV 2021

Greedy Gradient Ensemble for Robust Visual Question Answering ICCV 2021

Measuring Biases of Word Embeddings: What Similarity Measures and Descriptive Statistics to Use? NAACL 2021

Environment Inference for Invariant Learning ICML 2021

Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation AAAI 2021

Towards a unified framework for fair and stable graph representation learning UAI 2021

Addressing fairness in classification with a model-agnostic multi-objective algorithm UAI 2021

Debiasing Pre-trained Contextualised Embeddings EACL 2021

Memorization vs. Generalization : Quantifying Data Leakage in NLP Performance Evaluation EACL 2021

DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces EACL 2021

HateBERT: Retraining BERT for Abusive Language Detection in English IJCNLP 2021

Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets IJCNLP 2021

Algorithms for Fairness in Sequential Decision Making AISTATS 2021

Optimized Score Transformation for Consistent Fair Classification JMLR 2021

Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers NAACL 2021

Detoxifying Language Models Risks Marginalizing Minority Voices NAACL 2021

HONEST: Measuring Hurtful Sentence Completion in Language Models NAACL 2021

Fairness and Bias in Online Selection ICML 2021

Characterizing Fairness Over the Set of Good Models Under Selective Labels ICML 2021

Strategic Classification in the Dark ICML 2021

Fairness for Image Generation with Uncertain Sensitive Attributes ICML 2021

Fair Selective Classification Via Sufficiency ICML 2021

Blind Pareto Fairness and Subgroup Robustness ICML 2021

Testing Group Fairness via Optimal Transport Projections ICML 2021