Dear Colleagues,

Anomaly detection is an important task that tackles the problem of discovering data points or patterns in data that do not conform to normal behavior. Recognizing anomalies is critical for numerous high-impact applications in cyber-security, predictive maintenance, and rare disease diagnosis. Unfortunately, despite the recent developments in deep learning approaches, deep anomaly detection is significantly less explored than many other data mining tasks.

Transformer-based architectures are a brilliant example. They have topped the state-of-the-art charts in computer vision and natural language processing, but they are still under-explored for anomaly detection. This issue is due to the characteristics of anomalies (rarity, heterogeneity, unbounded nature, and absence of large data) that poorly fit the strengths of these algorithms in their standard configuration.

Furthermore, modern society also requires transparent decision processes. Therefore, the explanation of the anomaly has the same importance as its prediction. This fact is especially true for deep detection models applied in sensitive domains such as healthcare.

In this Special Issue, we welcome high-quality research papers addressing and reviewing theoretical and practical issues of deep learning systems focusing on anomaly detection tasks. We encourage solutions based on transformer architectures with explainable predictions or, in the case of graph-structured data, solutions that rely on graph neural networks.

Similarly, we welcome research papers on cutting-edge applications, including (but not limited to) cyber-security, predictive maintenance and defect detection, fraud detection, and rare disease/symptoms diagnosis.

Dr. Alessio Martino
Dr. Indro Spinelli
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. Algorithms 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.

• data mining
• machine learning
• deep learning
• anomaly detection
• explainable AI