FairNVT is a lightweight debiasing framework that injects calibrated Gaussian noise into sensitive embeddings learned by adapters for pretrained transformer-based encoders. By reducing sensitive-attribute leakage through orthogonality constraints and fairness regularization, it improves fairness metrics such as demographic parity difference and equalized odds while maintaining competitive task performance across vision and language datasets.
By Qiaoyue Tang, Sepidehsadat Hosseini, Mengyao Zhai, Thibaut Durand, Greg Mori
arXiv:2608. 14211v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training.
By Patrik Kenfack, Jesse C. Cresswell, Anthony L. Caterini, Samira Ebrahimi Kahou, Ulrich A\"ivodji
arXiv:2606. 31704v1 Announce Type: cross Abstract: The deployment of face detection models in real-world applications raises important fairness concerns, as these systems may showcase performance disparities across demographic groups.
By Maxime Moussi, Beno\^it Ronval, Siegfried Nijssen, F\'elicien Schiltz
arXiv:2606. 28097v1 Announce Type: new Abstract: Post-hoc controllability of fair machine learning models, the ability to control the trade-off between fairness and accuracy after training, is valuable for practical deployment.
By Maaya Sakata, Kazuto Fukuchi
arXiv:2609.16321v1 Announce Type: cross
Abstract: Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model dev...
By Archit Rathod, Saeid Tizpaz-Niari
arXiv:2404. 01356v3 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
By Xuran Li, Hao Xue, Peng Wu, Xingjun Ma, Zhen Zhang, Huaming Chen, Flora D. Salim
arXiv:2503.05684v2 Announce Type: replace-cross
Abstract: Pre-trained foundation models can be efficiently adapted for specific tasks using Low-Rank Adaptation (LoRA), but the fairness properties of...
By Parameswaran Kamalaruban, Mark Anderson, Stuart Burrell, Maeve Madigan, Piotr Skalski, David Sutton
The paper introduces a method called Debias Anything that jointly addresses fairness and diversity in diffusion models without requiring sensitive-attribute annotations. By connecting a frozen diffusion model to a pretrained vision-language embedding space via an adapter, the approach uses pairs of text prompts to guide batch composition toward desired attribute proportions and employs a disagreement score to promote diversity. The method is applicable to both unconditional and text-conditional diffusion models and demonstrates improved quality and diversity while maintaining comparable fairness levels in experiments.
By Th\'eau d'Audiffret, Mariia Vladimirova, Jean-Yves Franceschi
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
By Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini, Davide Talon, Elisa Ricci
The paper introduces a post‑processing framework that uses model ensembling to achieve fairness‑aware predictions. It is designed to work independently of any specific model internals, making it applicable to a wide range of learning tasks, model architectures, and fairness definitions. Experiments on classification, regression, and survival analysis show that the framework improves fairness while preserving predictive accuracy.
By Zhouting Zhao, Tin Lok James Ng
arXiv:2404. 01356v4 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
By Xuran Li, Hao Xue, Peng Wu, Xingjun Ma, Zhen Zhang, Huaming Chen, Flora D. Salim
arXiv:2607. 14705v1 Announce Type: new Abstract: Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race.
By Yuchang Zhu, Zezhong Xie, Huizhe Zhang, Huazhen Zhong, Jintang Li, Liang Chen, Zibin Zheng