scholarly journals TARA: Training and Representation Alteration for AI Fairness and Domain Generalization

2022 ◽  
pp. 1-38
Author(s):  
William Paul ◽  
Armin Hadzic ◽  
Neil Joshi ◽  
Fady Alajaji ◽  
Philippe Burlina
Keyword(s):  
Domain Adaptation ◽  
Representation Learning ◽  
Data Representation ◽  
Generative Models ◽  
Underrepresented Populations ◽  
Latent Space ◽  
Dual Strategy ◽  
Fine Control ◽  
Novel Method ◽  
And Training

Abstract We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias. It includes the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors and training set alteration via intelligent augmentation to address bias-causing data imbalance by using generative models that allow the fine control of sensitive factors related to underrepresented populations via domain adaptation and latent space manipulation. When testing our methods on image analytics, experiments demonstrate that TARA significantly or fully debiases baseline models while outperforming competing debiasing methods that have the same amount of information—for example, with (% overall accuracy, % accuracy gap) = (78.8, 0.5) versus the baseline method's score of (71.8, 10.5) for Eye-PACS, and (73.7, 11.8) versus (69.1, 21.7) for CelebA. Furthermore, recognizing certain limitations in current metrics used for assessing debiasing performance, we propose novel conjunctive debiasing metrics. Our experiments also demonstrate the ability of these novel metrics in assessing the Pareto efficiency of the proposed methods.

scholarly journals Generative models for capturing and exploiting the influence of process conditions on process curves

2021 ◽  
Author(s):  
Tarek Iraki ◽  
Norbert Link
Keyword(s):  
Latent Variable ◽  
Welding Process ◽  
Feature Space ◽  
Generative Models ◽  
Process Conditions ◽  
Process Data ◽  
Task Learning ◽  
Latent Space ◽  
Variable Space ◽  
Novel Method

AbstractVariations of dedicated process conditions (such as workpiece and tool properties) yield different process state evolutions, which are reflected by different time series of the observable quantities (process curves). A novel method is presented, which firstly allows to extract the statistical influence of these conditions on the process curves and its representation via generative models, and secondly represents their influence on the ensemble of curves by transformations of the representation space. A latent variable space is derived from sampled process data, which represents the curves with only few features. Generative models are formed based on conditional propability functions estimated in this space. Furthermore, the influence of conditions on the ensemble of process curves is represented by estimated transformations of the feature space, which map the process curve densities with different conditions on each other. The latent space is formed via Multi-Task-Learning of an auto-encoder and condition-detectors. The latter classifies the latent space representations of the process curves into the considered conditions. The Bayes framework and the Multi-task Learning models are used to obtain the process curve probabilty densities from the latent space densities. The methods are shown to reveal and represent the influence of combinations of workpiece and tool properties on resistance spot welding process curves.

scholarly journals A Survey of Unsupervised Generative Models for Exploratory Data Analysis and Representation Learning

2021 ◽  
Vol 54 (5) ◽  
pp. 1-40
Author(s):  
Mohanad Abukmeil ◽  
Stefano Ferrari ◽  
Angelo Genovese ◽  
Vincenzo Piuri ◽  
Fabio Scotti
Keyword(s):  
Big Data ◽  
Data Analysis ◽  
Exploratory Data Analysis ◽  
Representation Learning ◽  
Data Representation ◽  
Generative Models ◽  
Data Exploration ◽  
Generative Learning ◽  
Learning Models ◽  
Exploratory Data

For more than a century, the methods for data representation and the exploration of the intrinsic structures of data have developed remarkably and consist of supervised and unsupervised methods. However, recent years have witnessed the flourishing of big data, where typical dataset dimensions are high and the data can come in messy, incomplete, unlabeled, or corrupted forms. Consequently, discovering the hidden structure buried inside such data becomes highly challenging. From this perspective, exploratory data analysis plays a substantial role in learning the hidden structures that encompass the significant features of the data in an ordered manner by extracting patterns and testing hypotheses to identify anomalies. Unsupervised generative learning models are a class of machine learning models characterized by their potential to reduce the dimensionality, discover the exploratory factors, and learn representations without any predefined labels; moreover, such models can generate the data from the reduced factors’ domain. The beginner researchers can find in this survey the recent unsupervised generative learning models for the purpose of data exploration and learning representations; specifically, this article covers three families of methods based on their usage in the era of big data: blind source separation, manifold learning, and neural networks, from shallow to deep architectures.

scholarly journals Hyperspectral Image Classification with Localized Graph Convolutional Filtering

2021 ◽  
Vol 13 (3) ◽  
pp. 526
Author(s):  
Shengliang Pu ◽  
Yuanfeng Wu ◽  
Xu Sun ◽  
Xiaotong Sun
Keyword(s):  
Hyperspectral Image ◽  
Principal Component ◽  
Representation Learning ◽  
Classification Performance ◽  
Hyperspectral Data ◽  
Spectral Graph Theory ◽  
Feature Reduction ◽  
Graph Representation ◽  
Novel Method ◽  
Local Graph

The nascent graph representation learning has shown superiority for resolving graph data. Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships. Faced with hyperspectral image (HSI) classification, the priority problem might be how to convert hyperspectral data into irregular domains from regular grids. In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory. First, we conducted principal component analysis (PCA) preprocessing to create localized hyperspectral data cubes with unsupervised feature reduction. These feature cubes combined with localized adjacent matrices were fed into the popular graph convolution network in a standard supervised learning paradigm. Finally, we succeeded in analyzing diversified land covers by considering local graph structure with graph convolutional filtering. Experiments on real hyperspectral datasets demonstrated that the presented method offers promising classification performance compared with other popular competitors.

scholarly journals A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2111
Author(s):  
Bo-Wei Zhao ◽  
Zhu-Hong You ◽  
Lun Hu ◽  
Zhen-Hao Guo ◽  
Lei Wang ◽  
...  
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
Computational Models ◽  
Structural Information ◽  
Characteristic Curve ◽  
Representation Learning ◽  
Graph Representation ◽  
Convolutional Network ◽  
Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

Auto-weighted concept factorization for joint feature map and data representation learning

2021 ◽  
pp. 1-13
Author(s):  
Yikai Zhang ◽  
Yong Peng ◽  
Hongyu Bian ◽  
Yuan Ge ◽  
Feiwei Qin ◽  
...  
Keyword(s):  
Objective Function ◽  
Optimization Procedure ◽  
Feature Space ◽  
Representation Learning ◽  
Data Representation ◽  
Data Sets ◽  
Reconstruction Process ◽  
Factorization Model ◽  
Efficient Data ◽  
Concept Factorization

Concept factorization (CF) is an effective matrix factorization model which has been widely used in many applications. In CF, the linear combination of data points serves as the dictionary based on which CF can be performed in both the original feature space as well as the reproducible kernel Hilbert space (RKHS). The conventional CF treats each dimension of the feature vector equally during the data reconstruction process, which might violate the common sense that different features have different discriminative abilities and therefore contribute differently in pattern recognition. In this paper, we introduce an auto-weighting variable into the conventional CF objective function to adaptively learn the corresponding contributions of different features and propose a new model termed Auto-Weighted Concept Factorization (AWCF). In AWCF, on one hand, the feature importance can be quantitatively measured by the auto-weighting variable in which the features with better discriminative abilities are assigned larger weights; on the other hand, we can obtain more efficient data representation to depict its semantic information. The detailed optimization procedure to AWCF objective function is derived whose complexity and convergence are also analyzed. Experiments are conducted on both synthetic and representative benchmark data sets and the clustering results demonstrate the effectiveness of AWCF in comparison with the related models.

scholarly journals A Survey on Variational Autoencoders from a Green AI Perspective

2021 ◽  
Vol 2 (4) ◽  
Author(s):  
Andrea Asperti ◽  
Davide Evangelista ◽  
Elena Loli Piccolomini
Keyword(s):  
Architectural Design ◽  
Mathematical Formulation ◽  
Representation Learning ◽  
Generative Models ◽  
Model Description ◽  
Energetic Efficiency ◽  
Detailed Model ◽  
Latent Distribution ◽  
Quantitative Results ◽  
Generation Problem

AbstractVariational Autoencoders (VAEs) are powerful generative models that merge elements from statistics and information theory with the flexibility offered by deep neural networks to efficiently solve the generation problem for high-dimensional data. The key insight of VAEs is to learn the latent distribution of data in such a way that new meaningful samples can be generated from it. This approach led to tremendous research and variations in the architectural design of VAEs, nourishing the recent field of research known as unsupervised representation learning. In this article, we provide a comparative evaluation of some of the most successful, recent variations of VAEs. We particularly focus the analysis on the energetic efficiency of the different models, in the spirit of the so-called Green AI, aiming both to reduce the carbon footprint and the financial cost of generative techniques. For each architecture, we provide its mathematical formulation, the ideas underlying its design, a detailed model description, a running implementation and quantitative results.

Data Acquisition and Data Processing using Electroencephalogram in Neuromarketing: A Review

2021 ◽  
Vol 30 (1) ◽  
pp. 19-33
Author(s):  
Annis Shafika Amran ◽  
Sharifah Aida Sheikh Ibrahim ◽  
Nurul Hashimah Ahamed Hassain Malim ◽  
Nurfaten Hamzah ◽  
Putra Sumari ◽  
...  
Keyword(s):  
Data Acquisition ◽  
Linear Models ◽  
Brain Activity ◽  
Generative Models ◽  
Education Management ◽  
Latent Space ◽  
Latent Space Models ◽  
Cost Feasibility ◽  
Medical Healthcare ◽  
Electroencephalogram Eeg

Electroencephalogram (EEG) is a neurotechnology used to measure brain activity via brain impulses. Throughout the years, EEG has contributed tremendously to data-driven research models (e.g., Generalised Linear Models, Bayesian Generative Models, and Latent Space Models) in Neuroscience Technology and Neuroinformatic. Due to versatility, portability, cost feasibility, and non-invasiveness. It contributed to various Neuroscientific data that led to advancement in medical, education, management, and even the marketing field. In the past years, the extensive uses of EEG have been inclined towards medical healthcare studies such as in disease detection and as an intervention in mental disorders, but not fully explored for uses in neuromarketing. Hence, this study construes the data acquisition technique in neuroscience studies using electroencephalogram and outlines the trend of revolution of this technique in aspects of its technology and databases by focusing on neuromarketing uses.

scholarly journals Image Anomaly Detection Using Normal Data Only by Latent Space Resampling

2020 ◽  
Vol 10 (23) ◽  
pp. 8660
Author(s):  
Lu Wang ◽  
Dongkai Zhang ◽  
Jiahao Guo ◽  
Yuexing Han
Keyword(s):  
Anomaly Detection ◽  
Normal Distribution ◽  
Autoregressive Model ◽  
Probability Model ◽  
Latent Space ◽  
Industrial Inspection ◽  
Detection Stage ◽  
Novel Method ◽  
The Difference ◽  
Reconstruction Model

Detecting image anomalies automatically in industrial scenarios can improve economic efficiency, but the scarcity of anomalous samples increases the challenge of the task. Recently, autoencoder has been widely used in image anomaly detection without using anomalous images during training. However, it is hard to determine the proper dimensionality of the latent space, and it often leads to unwanted reconstructions of the anomalous parts. To solve this problem, we propose a novel method based on the autoencoder. In this method, the latent space of the autoencoder is estimated using a discrete probability model. With the estimated probability model, the anomalous components in the latent space can be well excluded and undesirable reconstruction of the anomalous parts can be avoided. Specifically, we first adopt VQ-VAE as the reconstruction model to get a discrete latent space of normal samples. Then, PixelSail, a deep autoregressive model, is used to estimate the probability model of the discrete latent space. In the detection stage, the autoregressive model will determine the parts that deviate from the normal distribution in the input latent space. Then, the deviation code will be resampled from the normal distribution and decoded to yield a restored image, which is closest to the anomaly input. The anomaly is then detected by comparing the difference between the restored image and the anomaly image. Our proposed method is evaluated on the high-resolution industrial inspection image datasets MVTec AD which consist of 15 categories. The results show that the AUROC of the model improves by 15% over autoencoder and also yields competitive performance compared with state-of-the-art methods.

scholarly journals A Novel Method for Acquiring Engineering-Oriented Operational Empirical Knowledge

2016 ◽  
Vol 2016 ◽  
pp. 1-19 ◽  
Author(s):  
Lijun Liu ◽  
Zuhua Jiang ◽  
Bo Song ◽  
Hongyuan Zhu ◽  
Xinyu Li
Keyword(s):  
Rough Set ◽  
Empirical Knowledge ◽  
New Employees ◽  
Know How ◽  
Time Standards ◽  
Novel Method ◽  
Variable Precision Rough Set ◽  
Basic Motion ◽  
And Training ◽  
Predetermined Time

The operational knowledge of skilled technicians gained from years of experience is invaluable for an enterprise. Possession of such knowledge will facilitate an enterprise sharing technician’s know-how and training of new employees effectively. However, until now there is rare efficient quantitative method to obtain this kind of tacit knowledge. In this paper we propose a concept of engineering-oriented operational empirical knowledge (OEK) to describe this kind of knowledge and design a framework to acquire OEK from skilled technician’s operations. The framework integrates motion analysis, motion elicitation, and intent analysis. The modular arrangement of predetermined time standards (MODAPTS) is used to divide the technician’s operational process into basic motion elements; and the variable precision rough set (VPRS) algorithm is used to extract the technician’s OEK content, which combined with the technician’s intent elicited via interview; the completed OEK is obtained. At the end of our study, an engineering case is used to validate the feasibility of the proposed method, which shows that satisfactory results have been reached for the study.

Sign in / Sign up

Export Citation Format

Share Document