arrow
Return

Graph Embedding With Data Uncertainty

delete2022-01-01
delete2
delete
OA
AI
F
Firas Laakom *
J
Jenni Raitoharju
N
Nikolaos Passalis
A
Alexandros Iosifidis
M
Moncef Gabbouj
DOI:10.1109/ACCESS.2022.3155233delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data. However, most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty. Thus, learning directly from raw data can be misleading and can negatively impact the accuracy. In this paper, we propose to model artifacts in training data using probability distributions; each data point is represented by a Gaussian distribution centered at the original data point and having a variance modeling its uncertainty. We reformulate the Graph Embedding framework to make it suitable for learning from distributions and we study as special cases the Linear Discriminant Analysis and the Marginal Fisher Analysis techniques. Furthermore, we propose two schemes for modeling data uncertainty based on pair-wise distances in an unsupervised and a supervised contexts.
Keywords:
Uncertainty
Data models
Principal component analysis
Optimization
Gaussian distribution
Eigenvalues and eigenfunctions
Training data
Graph embedding
subspace learning
dimensionality reduction
uncertainty estimation
spectral learning

Journal

IEEE Access cover
IEEE Access
IF:
3.6
Papers:
9.8W
Citations:
36.3W

Organization

F
Finnish Environment Institute
Scholars:
102
Papers: 54
Citations: 1.8K
A
Aarhus University
Scholars:
2.3K
Papers: 930
Citations: 2.9W
T
tampere university
Scholars:
588
Papers: 236
Citations: 7.8K
A
Aristotle University of Thessaloniki
Scholars:
1.2K
Papers: 437
Citations: 9.4K
researcher View more organizations
Cited Papers

Cited Papers

Graph Embedded One-Class Classifiers for media data classification
err2016-12-01
err36
errOAAI
errMygdalis, Vasileios; Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis
errShare
errSave
errShare
errSave
Robust Subspace Learning Robust PCA, robust subspace tracking, and robust subspace recovery
err2018-07-01
err282
errOAAI
errVaswani, Namrata; Bouwmans, Thierry; Javed, Sajid; Narayanamurthy, Praneeth
errShare
errSave
l1-Norm Heteroscedastic Discriminant Analysis Under Mixture of Gaussian Distributions
err2019-10-01
err10
PREAI
errZheng, Wenming; Lu, Cheng; Lin, Zhouchen; Zhang, Tong; Cui, Zhen; Yang, Wankou
errShare
errSave
errShare
errSave
errShare
errSave
researcher View more