Sampling Bias

Sampling bias, the systematic over- or under-representation of certain groups within a dataset, significantly impacts the accuracy and fairness of machine learning models. Current research focuses on developing methods to detect and mitigate this bias, employing techniques like Bayesian inference, neural networks (including variational autoencoders and novel architectures designed for bias correction), and active learning to identify and re-weight biased samples. Addressing sampling bias is crucial for improving the reliability and generalizability of models across diverse applications, ranging from credit scoring and ecological network analysis to medical image analysis and large language model development, ensuring fairer and more accurate outcomes.

Papers

August 23, 2024

Causal-Guided Active Learning for Debiasing Large Language Models
Li Du, Zhouhao Sun, Xiao Ding, Yixuan Ma, Yang Zhao, Kaitao Qiu, Ting Liu, Bing Qin
Active Learning Debiasing Method Sampling Bias

July 17, 2024

Fighting Sampling Bias: A Framework for Training and Evaluating Credit Scoring Models
Nikita Kozodoi, Stefan Lessmann, Morteza Alamgir, Luis Moreira-Matias, Konstantinos Papakonstantinou
Training Data New Framework Biased Training Based Rejection Sampling Bias Credit Scoring Model Scoring Model Probability Based Evaluation

March 4, 2024

Bipartite Graph Variational Auto-Encoder with Fair Latent Representation to Account for Sampling Bias in Ecological Networks
Emre Anakok, Pierre Barbillon, Colin Fontaine, Elisa Thebault
Latent Space Graph Embeddings Variational Graph Fair Representation Learning Sampling Bias Variational Graph Auto Mean End Account Ecological Network Bipartite Network

February 17, 2024

BiasBuster: a Neural Approach for Accurate Estimation of Population Statistics using Biased Location Data
Sepanta Zeighami, Cyrus Shahabi
Absolute Stance Bias Bias Evaluation Estimation Performance Neural Approach Sampling Bias Sample Specific Debiasing Population Data

January 2, 2024

Zero-Shot Position Debiasing for Large Language Models
Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Pengjie Ren, Zhumin Chen
Large Language Model Unsupervised Sentence Sampling Bias Position Bias

October 20, 2023

Foundation Model's Embedded Representations May Detect Distribution Shift
Max Vargas, Adam Tsou, Andrew Engel, Tony Chiang
Transfer Learning Foundation Model Distribution Shift Generalization Capacity Sampling Bias

June 19, 2023

Correcting Underrepresentation and Intersectional Bias for Classification
Emily Diana, Alexander Williams Tolbert
Classification Code Underrepresented Group PAC Learnability Intersectional Bias Sampling Bias VC Dimension

June 8, 2023

Shedding light on underrepresentation and Sampling Bias in machine learning
Sami Zhioua, Rūta Binkytė
Machine Learning Absolute Stance Bias Group DIscrimination Underrepresented Group Sampling Bias

May 26, 2023

On the Generalization and Approximation Capacities of Neural Controlled Differential Equations
Linus Bleistein, Agathe Guilloux
Neural Network Deep Neural Network Strong Generalization Supervised Learning Differential Equation Sampling Bias Approximation Power

April 17, 2023

Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations
Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, Peng Wu
Biased Datasets Biased Data Debiased Recommendation Unmeasured Confounding Sampling Bias Unbiased Evaluation Unbiased Meta Data

February 13, 2023

Provable Detection of Propagating Sampling Bias in Prediction Models
Pavan Ravishankar, Qingyu Mo, Edward McFowland, Daniel B. Neill
Absolute Stance Bias Accurate Detection Prediction Model Sampling Bias Data Bias

October 10, 2022

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning
Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou
Contrastive Learning Visual Question Answering Sampling Bias

September 5, 2022

Learning from a Biased Sample
Roshni Sahoo, Lihua Lei, Stefan Wager
LeArning Abstract Empirical Risk Minimization Data Driven Decision Sampling Bias

July 21, 2022

Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture
Jianwei Zhang, Dong Li, Lituan Wang, Lei Zhang
Data Augmentation Neural Architecture Medical Image Analysis Search Query Test Time Augmentation Self Augmentation Sampling Bias

May 30, 2022

Fool SHAP with Stealthily Biased Sampling
Gabriel Laberge, Ulrich Aïvodji, Satoshi Hara, Mario Marchand., Foutse Khomh
Black Box Model Fusion SHAP Sampling Bias Fairness Audit

March 30, 2022

To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo
Yiran Luo, Pratyay Banerjee, Tejas Gokhale, Yezhou Yang, Chitta Baral
MAESTRO Dataset Visual Grounding Biased Datasets Length Bias Contextual Cue Sampling Bias

March 11, 2022

Sampling Bias Correction for Supervised Machine Learning: A Bayesian Inference Approach with Practical Applications
Max Sklar
Bayesian Inference Logistic Regression Practical Application Supervised Machine Learning Statistical Inference Sampling Bias Bayesian Inference Framework

December 30, 2021

Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Data
Shenwang Jiang, Jianan Li, Ying Wang, Bo Huang, Zhang Zhang, Tingfa Xu
Imbalanced Data Biased Training Sampling Bias Sample Reweighting Sample Loss