Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds

• URL: http://arxiv.org/abs/2303.12307v5
• Date: Fri, 17 May 2024 07:00:58 GMT
• Title: Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
• Authors: Yanbiao Ma, Licheng Jiao, Fang Liu, Maoji Wen, Lingling Li, Wenping Ma, Shuyuan Yang, Xu Liu, Puhua Chen,
• Abstract summary: Recent studies have shown that tail classes are not always hard to learn, and model bias has been observed on sample-balanced datasets. In this work, we first establish a geometric perspective for analyzing model fairness and then systematically propose a series of geometric measurements.
• Score: 44.79535333220044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes. However, recent studies have shown that tail classes are not always hard to learn, and model bias has been observed on sample-balanced datasets, suggesting the existence of other factors that affect model bias. In this work, we first establish a geometric perspective for analyzing model fairness and then systematically propose a series of geometric measurements for perceptual manifolds in deep neural networks. Subsequently, we comprehensively explore the effect of the geometric characteristics of perceptual manifolds on classification difficulty and how learning shapes the geometric characteristics of perceptual manifolds. An unanticipated finding is that the correlation between the class accuracy and the separation degree of perceptual manifolds gradually decreases during training, while the negative correlation with the curvature gradually increases, implying that curvature imbalance leads to model bias.Building upon these observations, we propose curvature regularization to facilitate the model to learn curvature-balanced and flatter perceptual manifolds. Evaluations on multiple long-tailed and non-long-tailed datasets show the excellent performance and exciting generality of our approach, especially in achieving significant performance improvements based on current state-of-the-art techniques. Our work opens up a geometric analysis perspective on model bias and reminds researchers to pay attention to model bias on non-long-tailed and even sample-balanced datasets.

Related papers

• Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification [47.09355487357069]
  We propose to leverage the geometric information of the feature distribution of the well-represented head class to guide the model to learn the underlying distribution of the tail class. It aims to make the perturbed features cover the underlying distribution of the tail class as much as possible, thus improving the model's generalization performance in the test domain.
  arXiv  Detail & Related papers  (2024-01-21T09:16:29Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning [68.76846801719095]
  We show that double descent appears exactly when and where it occurs, and that its location is not inherently tied to the threshold p=n. This provides a resolution to tensions between double descent and statistical intuition.
  arXiv  Detail & Related papers  (2023-10-29T12:05:39Z)
• Delving into Semantic Scale Imbalance [45.30062061215943]
  We define and quantify the semantic scale of classes, which is used to measure the feature diversity of classes. We propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework. Comprehensive experiments show that dynamic semantic-scale-balanced learning consistently enables the model to perform superiorly on large-scale long-tailed and non-long-tailed natural and medical datasets.
  arXiv  Detail & Related papers  (2022-12-30T09:40:09Z)
• Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures [14.578025146641806]
  We provide a full and unified analysis of the whole time-evolution of the generalization curve. We show that our theoretical predictions adequately match the learning curves obtained by gradient descent over realistic datasets.
  arXiv  Detail & Related papers  (2022-12-13T17:39:18Z)
• Bias-inducing geometries: an exactly solvable data model with fairness implications [13.690313475721094]
  We introduce an exactly solvable high-dimensional model of data imbalance. We analytically unpack the typical properties of learning models trained in this synthetic framework. We obtain exact predictions for the observables that are commonly employed for fairness assessment.
  arXiv  Detail & Related papers  (2022-05-31T16:27:57Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.