Fairness

Sustainable Modular Debiasing of Language Models EMNLP 2021 Teaching the Old Dog New Tricks: Supervised Learning with Constraints AAAI 2021 Testing Group Fairness via Optimal Transport Projections ICML 2021 Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects EMNLP 2021 The Affective Growth of Computer Vision CVPR 2021 The Effect of Round-Trip Translation on Fairness in Sentiment Analysis EMNLP 2021 The Gap on Gap: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets AAAI 2021 The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective AAAI 2021 Themis: A Fair Evaluation Platform for Computer Vision Competitions IJCAI 2021 The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color EMNLP 2021 Tilted Empirical Risk Minimization ICLR 2021 To be Robust or to be Fair: Towards Fairness in Adversarial Training ICML 2021 Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers NAACL 2021 Towards a unified framework for fair and stable graph representation learning UAI 2021 Towards Automatic Bias Detection in Knowledge Graphs EMNLP 2021 Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective NeurIPS 2021 Towards Equal Gender Representation in the Annotations of Toxic Language Detection ACL 2021 Towards Fair and Transparent Algorithmic Systems IJCAI 2021 Towards Fair Cross-Domain Adaptation via Generative Learning WACV 2021 Towards Fair, Equitable, and Efficient Peer Review AAAI 2021 Towards Reducing Biases in Combining Multiple Experts Online IJCAI 2021 Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration AAAI 2021 Towards Understanding and Mitigating Social Biases in Language Models ICML 2021 Towards Understanding the Role of Gender in Deploying Social Media-Based Mental Health Surveillance Models NAACL 2021 Training Over-parameterized Models with Non-decomposable Objectives NeurIPS 2021