Advances in Explainable Artificial Intelligence

A special issue of Information (ISSN 2078-2489). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: closed (28 September 2023) | Viewed by 48033

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science, Università degli Studi di Milano, 20122 Milano, MI, Italy
Interests: machine learning; computational intelligence; game theory applications to machine learning and networking
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science and Information Technology of INSA Lyon, LIRIS laboratory, 69100 Villeurbanne, France
Interests: machine learning; semantic web; information retrieval
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine Learning (ML)-based Artificial Intelligence (AI) algorithms can learn from known examples of various abstract representations and models that, once applied to unknown examples, can perform classification, regression or forecasting tasks, to name a few.

Very often, these highly effective ML representations are difficult to understand; this holds true particularly for deep learning models, which can involve millions of parameters. However, for many applications, it is of utmost importance for the stakeholders to understand the decisions made by the system, in order to use them better. Furthermore, for decisions that affect an individual, the legislation might even advocate in the future a “right to an explanation”. Overall, improving the algorithms’ explainability may foster trust and social acceptance of AI.

The need to make ML algorithms more transparent and more explainable has generated several lines of research that form an area known as explainable Artificial Intelligence (XAI). 

Among the goals of XAI are adding transparency to ML models by providing detailed information about why the system has reached a particular decision; designing more explainable and transparent ML models, while at the same time maintaining high performance levels; finding a way to evaluate the overall explainability and transparency of the models and quantifying their effectiveness for different stakeholders.

The objective of this Special Issue is to explore recent advances and techniques in the XAI area.

Research topics of interest include (but are not limited to):
- Devising machine learning models that are transparent-by-design;

- Planning for transparency, from data collection up to training, test, and production;

- Developing algorithms and user interfaces for explainability;

- Identifying and mitigating biases in data collection;

- Performing black-box model auditing and explanation;

- Detecting data bias and algorithmic bias;

- Learning causal relationships;

- Integrating social and ethical aspects of explainability;

- Integrating explainability into existing AI systems;

- Designing new explanation modalities;

- Exploring theoretical aspects of explanation and interpretability;

- Investigating the use of XAI in application sectors such as healthcare, bioinformatics, multimedia, linguistics, human–computer interaction, machine translation, autonomous vehicles, risk assessment, justice, etc.

Prof. Dr. Gabriele Gianini
Prof. Dr. Pierre-Edouard Portier
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • deep learning
  • explainability
  • transparency
  • accountability

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Related Special Issue

Published Papers (11 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 4732 KiB  
Article
Interpreting Disentangled Representations of Person-Specific Convolutional Variational Autoencoders of Spatially Preserving EEG Topographic Maps via Clustering and Visual Plausibility
by Taufique Ahmed and Luca Longo
Information 2023, 14(9), 489; https://doi.org/10.3390/info14090489 - 4 Sep 2023
Cited by 2 | Viewed by 1603
Abstract
Dimensionality reduction and producing simple representations of electroencephalography (EEG) signals are challenging problems. Variational autoencoders (VAEs) have been employed for EEG data creation, augmentation, and automatic feature extraction. In most of the studies, VAE latent space interpretation is used to detect only the [...] Read more.
Dimensionality reduction and producing simple representations of electroencephalography (EEG) signals are challenging problems. Variational autoencoders (VAEs) have been employed for EEG data creation, augmentation, and automatic feature extraction. In most of the studies, VAE latent space interpretation is used to detect only the out-of-order distribution latent variable for anomaly detection. However, the interpretation and visualisation of all latent space components disclose information about how the model arrives at its conclusion. The main contribution of this study is interpreting the disentangled representation of VAE by activating only one latent component at a time, whereas the values for the remaining components are set to zero because it is the mean of the distribution. The results show that CNN-VAE works well, as indicated by matrices such as SSIM, MSE, MAE, and MAPE, along with SNR and correlation coefficient values throughout the architecture’s input and output. Furthermore, visual plausibility and clustering demonstrate that each component contributes differently to capturing the generative factors in topographic maps. Our proposed pipeline adds to the body of knowledge by delivering a CNN-VAE-based latent space interpretation model. This helps us learn the model’s decision and the importance of each component of latent space responsible for activating parts of the brain. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

16 pages, 1690 KiB  
Article
Revisiting Softmax for Uncertainty Approximation in Text Classification
by Andreas Nugaard Holm, Dustin Wright and Isabelle Augenstein
Information 2023, 14(7), 420; https://doi.org/10.3390/info14070420 - 20 Jul 2023
Cited by 3 | Viewed by 1888
Abstract
Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) dropout, which is computationally expensive as it requires multiple forward passes through the model. [...] Read more.
Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) dropout, which is computationally expensive as it requires multiple forward passes through the model. A cheaper alternative is to simply use a softmax based on a single forward pass without dropout to estimate model uncertainty. However, prior work has indicated that these predictions tend to be overconfident. In this paper, we perform a thorough empirical analysis of these methods on five datasets with two base neural architectures in order to identify the trade-offs between the two. We compare both softmax and an efficient version of MC dropout on their uncertainty approximations and downstream text classification performance, while weighing their runtime (cost) against performance (benefit). We find that, while MC dropout produces the best uncertainty approximations, using a simple softmax leads to competitive, and in some cases better, uncertainty estimation for text classification at a much lower computational cost, suggesting that softmax can in fact be a sufficient uncertainty estimate when computational resources are a concern. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

17 pages, 486 KiB  
Article
Exploring Neural Dynamics in Source Code Processing Domain
by Martina Saletta and Claudio Ferretti
Information 2023, 14(4), 251; https://doi.org/10.3390/info14040251 - 21 Apr 2023
Viewed by 1518
Abstract
Deep neural networks have proven to be able to learn rich internal representations, including for features that can also be used for different purposes than those the networks are originally developed for. In this paper, we are interested in exploring such ability and, [...] Read more.
Deep neural networks have proven to be able to learn rich internal representations, including for features that can also be used for different purposes than those the networks are originally developed for. In this paper, we are interested in exploring such ability and, to this aim, we propose a novel approach for investigating the internal behavior of networks trained for source code processing tasks. Using a simple autoencoder trained in the reconstruction of vectors representing programs (i.e., program embeddings), we first analyze the performance of the internal neurons in classifying programs according to different labeling policies inspired by real programming issues, showing that some neurons can actually detect different program properties. We then study the dynamics of the network from an information-theoretic standpoint, namely by considering the neurons as signaling systems and by computing the corresponding entropy. Further, we define a way to distinguish neurons according to their behavior, to consider them as formally associated with different abstract concepts, and through the application of nonparametric statistical tests to pairs of neurons, we look for neurons with unique (or almost unique) associated concepts, showing that the entropy value of a neuron is related to the rareness of its concept. Finally, we discuss how the proposed approaches for ranking the neurons can be generalized to different domains and applied to more sophisticated and specialized networks so as to help the research in the growing field of explainable artificial intelligence. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

19 pages, 923 KiB  
Article
Explainabilty Comparison between Random Forests and Neural Networks—Case Study of Amino Acid Volume Prediction
by Roberta De Fazio, Rosy Di Giovannantonio, Emanuele Bellini and Stefano Marrone
Information 2023, 14(1), 21; https://doi.org/10.3390/info14010021 - 29 Dec 2022
Cited by 2 | Viewed by 1920
Abstract
As explainability seems to be the driver for a wiser adoption of Artificial Intelligence in healthcare and in critical applications, in general, a comprehensive study of this field is far from being completed. On one hand, a final definition and theoretical measurements of [...] Read more.
As explainability seems to be the driver for a wiser adoption of Artificial Intelligence in healthcare and in critical applications, in general, a comprehensive study of this field is far from being completed. On one hand, a final definition and theoretical measurements of explainability have not been assessed, yet, on the other hand, some tools and frameworks for the practical evaluation of this feature are now present. This paper aims to present a concrete experience in using some of these explainability-related techniques in the problem of predicting the size of amino acids in real-world protein structures. In particular, the feature importance calculation embedded in Random Forest (RF) training is compared with the results of the Eli-5 tool applied to the Neural Network (NN) model. Both the predictors are trained on the same dataset, which is extracted from Protein Data Bank (PDB), considering 446 myoglobins structures and process it with several tools to implement a geometrical model and perform analyses on it. The comparison between the two models draws different conclusions about the residues’ geometry and their biological properties. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

12 pages, 2020 KiB  
Article
Justifying Arabic Text Sentiment Analysis Using Explainable AI (XAI): LASIK Surgeries Case Study
by Youmna Abdelwahab, Mohamed Kholief and Ahmed Ahmed Hesham Sedky
Information 2022, 13(11), 536; https://doi.org/10.3390/info13110536 - 11 Nov 2022
Cited by 6 | Viewed by 3541
Abstract
With the increasing use of machine learning across various fields to address several aims and goals, the complexity of the ML and Deep Learning (DL) approaches used to provide solutions has also increased. In the last few years, Explainable AI (XAI) methods to [...] Read more.
With the increasing use of machine learning across various fields to address several aims and goals, the complexity of the ML and Deep Learning (DL) approaches used to provide solutions has also increased. In the last few years, Explainable AI (XAI) methods to further justify and interpret deep learning models have been introduced across several domains and fields. While most papers have applied XAI to English and other Latin-based languages, this paper aims to explain attention-based long short-term memory (LSTM) results across Arabic Sentiment Analysis (ASA), which is considered an uncharted area in previous research. With the use of Local Interpretable Model-agnostic Explanation (LIME), we intend to further justify and demonstrate how the LSTM leads to the prediction of sentiment polarity within ASA in domain-specific Arabic texts regarding medical insights on LASIK surgery across Twitter users. In our research, the LSTM reached an accuracy of 79.1% on the proposed data set. Throughout the representation of sentiments using LIME, it demonstrated accurate results regarding how specific words contributed to the overall sentiment polarity classification. Furthermore, we compared the word count with the probability weights given across the examples, in order to further validate the LIME results in the context of ASA. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

18 pages, 402 KiB  
Article
Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing
by Shailza Jolly, Pepa Atanasova and Isabelle Augenstein
Information 2022, 13(10), 500; https://doi.org/10.3390/info13100500 - 17 Oct 2022
Cited by 6 | Viewed by 2992
Abstract
Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of these explanations is expensive and time-consuming. Recent work has used extractive summarization to select a [...] Read more.
Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of these explanations is expensive and time-consuming. Recent work has used extractive summarization to select a sufficient subset of the most important facts from the ruling comments (RCs) of a professional journalist to obtain fact-checking explanations. However, these explanations lack fluency and sentence coherence. In this work, we present an iterative edit-based algorithm that uses only phrase-level edits to perform unsupervised post-editing of disconnected RCs. To regulate our editing algorithm, we use a scoring function with components including fluency and semantic preservation. In addition, we show the applicability of our approach in a completely unsupervised setting. We experiment with two benchmark datasets, namely LIAR-PLUS and PubHealth. We show that our model generates explanations that are fluent, readable, non-redundant, and cover important information for the fact check. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

25 pages, 1402 KiB  
Article
Constructing Explainable Classifiers from the Start—Enabling Human-in-the Loop Machine Learning
by Vladimir Estivill-Castro, Eugene Gilmore and René Hexel
Information 2022, 13(10), 464; https://doi.org/10.3390/info13100464 - 29 Sep 2022
Cited by 2 | Viewed by 2353
Abstract
Interactive machine learning (IML) enables the incorporation of human expertise because the human participates in the construction of the learned model. Moreover, with human-in-the-loop machine learning (HITL-ML), the human experts drive the learning, and they can steer the learning objective not only for [...] Read more.
Interactive machine learning (IML) enables the incorporation of human expertise because the human participates in the construction of the learned model. Moreover, with human-in-the-loop machine learning (HITL-ML), the human experts drive the learning, and they can steer the learning objective not only for accuracy but perhaps for characterisation and discrimination rules, where separating one class from others is the primary objective. Moreover, this interaction enables humans to explore and gain insights into the dataset as well as validate the learned models. Validation requires transparency and interpretable classifiers. The huge relevance of understandable classification has been recently emphasised for many applications under the banner of explainable artificial intelligence (XAI). We use parallel coordinates to deploy an IML system that enables the visualisation of decision tree classifiers but also the generation of interpretable splits beyond parallel axis splits. Moreover, we show that characterisation and discrimination rules are also well communicated using parallel coordinates. In particular, we report results from the largest usability study of a IML system, confirming the merits of our approach. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

14 pages, 4173 KiB  
Article
Federated Learning of Explainable AI Models in 6G Systems: Towards Secure and Automated Vehicle Networking
by Alessandro Renda, Pietro Ducange, Francesco Marcelloni, Dario Sabella, Miltiadis C. Filippou, Giovanni Nardini, Giovanni Stea, Antonio Virdis, Davide Micheli, Damiano Rapone and Leonardo Gomes Baltar
Information 2022, 13(8), 395; https://doi.org/10.3390/info13080395 - 20 Aug 2022
Cited by 38 | Viewed by 6332
Abstract
This article presents the concept of federated learning (FL) of eXplainable Artificial Intelligence (XAI) models as an enabling technology in advanced 5G towards 6G systems and discusses its applicability to the automated vehicle networking use case. Although the FL of neural networks has [...] Read more.
This article presents the concept of federated learning (FL) of eXplainable Artificial Intelligence (XAI) models as an enabling technology in advanced 5G towards 6G systems and discusses its applicability to the automated vehicle networking use case. Although the FL of neural networks has been widely investigated exploiting variants of stochastic gradient descent as the optimization method, it has not yet been adequately studied in the context of inherently explainable models. On the one side, XAI permits improving user experience of the offered communication services by helping end users trust (by design) that in-network AI functionality issues appropriate action recommendations. On the other side, FL ensures security and privacy of both vehicular and user data across the whole system. These desiderata are often ignored in existing AI-based solutions for wireless network planning, design and operation. In this perspective, the article provides a detailed description of relevant 6G use cases, with a focus on vehicle-to-everything (V2X) environments: we describe a framework to evaluate the proposed approach involving online training based on real data from live networks. FL of XAI models is expected to bring benefits as a methodology for achieving seamless availability of decentralized, lightweight and communication efficient intelligence. Impacts of the proposed approach (including standardization perspectives) consist in a better trustworthiness of operations, e.g., via explainability of quality of experience (QoE) predictions, along with security and privacy-preserving management of data from sensors, terminals, users and applications. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

15 pages, 400 KiB  
Article
Bias Discovery in Machine Learning Models for Mental Health
by Pablo Mosteiro, Jesse Kuiper, Judith Masthoff, Floortje Scheepers and Marco Spruit
Information 2022, 13(5), 237; https://doi.org/10.3390/info13050237 - 5 May 2022
Cited by 9 | Viewed by 3990
Abstract
Fairness and bias are crucial concepts in artificial intelligence, yet they are relatively ignored in machine learning applications in clinical psychiatry. We computed fairness metrics and present bias mitigation strategies using a model trained on clinical mental health data. We collected structured data [...] Read more.
Fairness and bias are crucial concepts in artificial intelligence, yet they are relatively ignored in machine learning applications in clinical psychiatry. We computed fairness metrics and present bias mitigation strategies using a model trained on clinical mental health data. We collected structured data related to the admission, diagnosis, and treatment of patients in the psychiatry department of the University Medical Center Utrecht. We trained a machine learning model to predict future administrations of benzodiazepines on the basis of past data. We found that gender plays an unexpected role in the predictions—this constitutes bias. Using the AI Fairness 360 package, we implemented reweighing and discrimination-aware regularization as bias mitigation strategies, and we explored their implications for model performance. This is the first application of bias exploration and mitigation in a machine learning model trained on real clinical psychiatry data. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

29 pages, 1619 KiB  
Article
Explainable AI for Psychological Profiling from Behavioral Data: An Application to Big Five Personality Predictions from Financial Transaction Records
by Yanou Ramon, R.A. Farrokhnia, Sandra C. Matz and David Martens
Information 2021, 12(12), 518; https://doi.org/10.3390/info12120518 - 13 Dec 2021
Cited by 12 | Viewed by 7901
Abstract
Every step we take in the digital world leaves behind a record of our behavior; a digital footprint. Research has suggested that algorithms can translate these digital footprints into accurate estimates of psychological characteristics, including personality traits, mental health or intelligence. The mechanisms [...] Read more.
Every step we take in the digital world leaves behind a record of our behavior; a digital footprint. Research has suggested that algorithms can translate these digital footprints into accurate estimates of psychological characteristics, including personality traits, mental health or intelligence. The mechanisms by which AI generates these insights, however, often remain opaque. In this paper, we show how Explainable AI (XAI) can help domain experts and data subjects validate, question, and improve models that classify psychological traits from digital footprints. We elaborate on two popular XAI methods (rule extraction and counterfactual explanations) in the context of Big Five personality predictions (traits and facets) from financial transactions data (N = 6408). First, we demonstrate how global rule extraction sheds light on the spending patterns identified by the model as most predictive for personality, and discuss how these rules can be used to explain, validate, and improve the model. Second, we implement local rule extraction to show that individuals are assigned to personality classes because of their unique financial behavior, and there exists a positive link between the model’s prediction confidence and the number of features that contributed to the prediction. Our experiments highlight the importance of both global and local XAI methods. By better understanding how predictive models work in general as well as how they derive an outcome for a particular person, XAI promotes accountability in a world in which AI impacts the lives of billions of people around the world. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

16 pages, 1607 KiB  
Article
Learnable Leaky ReLU (LeLeLU): An Alternative Accuracy-Optimized Activation Function
by Andreas Maniatopoulos and Nikolaos Mitianoudis
Information 2021, 12(12), 513; https://doi.org/10.3390/info12120513 - 9 Dec 2021
Cited by 34 | Viewed by 8550
Abstract
In neural networks, a vital component in the learning and inference process is the activation function. There are many different approaches, but only nonlinear activation functions allow such networks to compute non-trivial problems by using only a small number of nodes, and such [...] Read more.
In neural networks, a vital component in the learning and inference process is the activation function. There are many different approaches, but only nonlinear activation functions allow such networks to compute non-trivial problems by using only a small number of nodes, and such activation functions are called nonlinearities. With the emergence of deep learning, the need for competent activation functions that can enable or expedite learning in deeper layers has emerged. In this paper, we propose a novel activation function, combining many features of successful activation functions, achieving 2.53% higher accuracy than the industry standard ReLU in a variety of test cases. Full article
(This article belongs to the Special Issue Advances in Explainable Artificial Intelligence)
Show Figures

Figure 1

Back to TopTop