Hugging Face Trending Papers October 28, 2026

FairSplit: Decomposing the Embedding Space for Fair Classification

Read the original on Hugging Face Trending Papers →

FairSplit decomposes the embedding space into a Fair Space for prediction and a Sensitive Space that isolates sensitive information, using a learnable mask and the Hilbert‑Schmidt Independence Criterion (HSIC) to guide the separation. The method simultaneously trains for classification accuracy and independence from sensitive attributes, providing theoretical bounds on the demographic parity gap based on the Fair Space dimensionality and HSIC. It supports multiclass tasks and non‑binary sensitive attributes, achieving competitive accuracy‑fairness trade‑offs on established benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 2

Demystifying the Optimal Fair Classifier in Multi-Class Classification

arXiv:2606. 00656v1 Announce Type: cross Abstract: Ensuring fair and equitable treatment across diverse groups, particularly in multi-class classification tasks, poses a significant challenge due to the persistent biases inherent in machine learning models.

By Li Zhang, Yuyuan Li, XiaoHua Feng, Jiaming Zhang, Fengyuan Yu, Chaochao Chen

fine-tuning safety

arXiv AI

Aug 19

FairNVT: Fair Classification via Noise Injection in Vision Transformers

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

llms rag safety

arXiv Machine Learning

Jul 14

Fairness Constraints in High-Dimensional Generalized Linear Models

arXiv:2604. 16610v2 Announce Type: replace-cross Abstract: Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability.

By Yixiao Lin, James Booth

safety

arXiv Computer Vision

Aug 25

Fairness-Aware Low-Rank Representation Fine-Tuning

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

fine-tuning safety

arXiv Machine Learning

Jun 19

Data Bias Mitigation under Coverage Constraints & The Price of Fairness

arXiv:2606. 20461v1 Announce Type: new Abstract: Machine learning models have been shown to exhibit discriminatory outcomes or degraded performance for individuals at the intersection of multiple sensitive attributes, such as race and gender.

By Bruno Scarone, Alfredo Viola, Ren\'ee J. Miller

safety

arXiv AI

Jun 4

Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods

arXiv:2511. 03304v2 Announce Type: replace-cross Abstract: With the on-going integration of machine learning systems into the everyday social life of millions the notion of fairness becomes an ever increasing priority in their development.

By Felix St\"orck, Fabian Hinder, Barbara Hammer

rag safety

One email a morning, machine-written

Related stories

Demystifying the Optimal Fair Classifier in Multi-Class Classification

FairNVT: Fair Classification via Noise Injection in Vision Transformers

Fairness Constraints in High-Dimensional Generalized Linear Models

Fairness-Aware Low-Rank Representation Fine-Tuning

Data Bias Mitigation under Coverage Constraints & The Price of Fairness

Extending Fair Null-Space Projections for Continuous Attributes to Kernel Methods