bias mitigation
Bias mitigation involves strategies and techniques aimed at reducing biases in AI models' predictions or outcomes, ensuring fairness and equity in decision-making processes.
- Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach
- Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport
- EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition
- FairDD: Fair Dataset Distillation
- Fairness-aware Anomaly Detection via Fair Projection
- How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective
- LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
- Matchings Under Biased and Correlated Evaluations
- Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts