5 papers
A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks
Tangzheng Lian, Guanyu Hu, Yijing Ren +2
While Vision-Language Models (VLMs) have achieved remarkable performance across diverse downstream tasks, recent studies have shown that they can inherit social biases from the tra…
Fair Domain Generalization: An Information-Theoretic View
Tangzheng Lian, Guanyu Hu, Dimitrios Kollias +2
Domain generalization (DG) and algorithmic fairness are two critical challenges in machine learning. However, most DG methods focus only on minimizing expected risk in the unseen t…
FairMT: Fairness for Heterogeneous Multi-Task Learning
Guanyu Hu, Tangzheng Lian, Na Yan +5
Fairness in machine learning has been extensively studied in single-task settings, while fair multi-task learning (MTL), especially with heterogeneous tasks (classification, detect…
CausalAffect: Causal Discovery for Facial Affective Understanding
Guanyu Hu, Tangzheng Lian, Dimitrios Kollias +2
Understanding human affect from facial behavior requires not only accurate recognition but also structured reasoning over the latent dependencies that drive muscle activations and…
A Feature-level Bias Evaluation Framework for Facial Expression Recognition Models
Tangzheng Lian, Oya Celiktutan
Recent studies on fairness have shown that Facial Expression Recognition (FER) models exhibit biases toward certain visually perceived demographic groups. However, the limited avai…