Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds
Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence. Delving into deeper factors that affect the fairness of DNNs is paramount and serves as the foundation for mitigating model biases. However, current methods are limited in accurately predicting DNN biases, relying solely on the number of training samples and lacking more precise measurement tools. Here, we establish a geometric perspective for analyzing the fairness of DNNs, comprehensively exploring how DNNs internally shape the intrinsic geometric characteristics of datasets-the intrinsic dimensions (IDs) of perceptual manifolds, and the impact of IDs on the fairness of DNNs. Based on multiple findings, we propose Intrinsic Dimension Regularization (IDR), which enhances the fairness and performance of models by promoting the learning of concise and ID-balanced class perceptual manifolds. In various image recognition benchmark tests, IDR significantly mitigates model bias while improving its performance.
Code (1)
Tasks
FairnessSimilar Papers 제목 키워드 기반
Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models
The advancement of large language models (LLMs) has demonstrated strong capabilities across various applications, including mental health analysis. However, existing studies have focused on predictive performance, leavin…
FairnessUniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt …
In-Context LearningUnveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness
excel in delivering comprehensive suggestions by deeply analyzing content and user behavior. However, they often inherit biases from skewed training data, favoring mainstream content while underrepresenting diverse or no…
FairnessLanguage ModelingLanguage ModellingLarge Language Model+3Investigating Societal Biases in a Poetry Composition System
There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative languag…
Data AugmentationRetrievalStyle TransferUncertainty-Aware Credit Card Fraud Detection Using Deep Learning
Countless research works of deep neural networks (DNNs) in the task of credit card fraud detection have focused on improving the accuracy of point predictions and mitigating unwanted biases by building different network …
Deep LearningFraud DetectionUncertainty Quantification