Debiased ML

ML: Machine Learning

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

FairNVT: Improving Fairness via Noise Injection in Vision Transformers
Apr 18, 2026Qiaoyue Tang, Sepidehsadat Hosseini, Mengyao Zhai +2Representation Learning Debiased ML
University of British Columbia · RBC Borealis · Simon Fraser University
Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement
Jan 29, 2026Jinhao Pan, Chahat Raj, Anjishnu Mukherjee +4Debiased ML Social Bias in Language Models
Department of Computer Science, George Mason University, Fairfax, VA, USA · Lightridge High School, Aldie, VA, USA
SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence
Dec 6, 2024Bowei Tian, Yexiao He, Ziyao Wang +3Debiased ML Algorithmic Fairness
University of Maryland, College Park, MD 20742, USA · Clemson University, Clemson, SC 29634, USA
General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level
Nov 23, 2023Bingkang Shi, Xiaodan Zhang, Dehan Kong +4Gender Bias in Language Models Debiased ML
Chinese Academy of Sciences, Institute of Information Engineering, Beijing 100093, China · Alibaba Group, Alibaba Artificial Intelligence Governance Laboratory, Beijing, China · University of Bristol, Department of Electrical and Electronic Engineering, Bristol, BS8 1UB, UK

Apr 18, 2026, cs.CVJ/K move · Enter open · S save

FairNVT: Improving Fairness via Noise Injection in Vision Transformers

Qiaoyue Tang, Sepidehsadat Hosseini, Mengyao Zhai, Thibaut Durand+1

University of British Columbia · RBC Borealis · Simon Fraser University

Representation Learning Debiased ML Vision Transformer Algorithmic Fairness

Open paper AskPDF arXiv

This paper presents FairNVT, a lightweight debiasing framework for pretrained transformer-based encoders that improves both representation and prediction level fairness while preserving task accuracy. Unlike many existing debiasing approaches that address these notions separately, we argue they are inherently connected: suppressing sensitive information at the representation level can facilitate fairer predictions. Our approach learns task-relevant and sensitive embeddings via lightweight adapters, applies calibrated Gaussian noise to the sensitive embedding, and fuses it with the task representation. Together with orthogonality constraints and fairness regularization, these components jointly reduce sensitive-attribute leakage in the learned embeddings and encourage fairer downstream predictions. The framework is compatible with a wide range of pretrained transformer encoders. Across three datasets spanning vision and language, FairNVT reduces sensitive-attribute attacker accuracy, improves demographic-parity and equalized-odds metrics, and maintains high task performance.

Momentum

Related topics

Latest papers 34

FairNVT: Improving Fairness via Noise Injection in Vision Transformers

Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement

SPARC: Scalable Path-Specific Counterfactual Fairness via Causal Conditional Independence

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level