applsci-logo

Journal Browser

Journal Browser

Robust and Reliable Neural Networks for Real-World Data

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 2081

Editor


E-Mail Website
Guest Editor
School of Information Technology and Electronic Engineering, The University of Queensland, Brisbane, QLD 4072, Australia
Interests: big data; natural language processing; knowledge graph; Internet of Things
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

This Special Issue focuses on the development and application of robust and reliable deep neural network (DNN) methodologies for real-world data, where noise, incompleteness, heterogeneity, and uncertainty are common challenges. It aims to highlight innovative approaches that enhance the performance, stability, and interpretability of neural network models across diverse application domains.

Topics of interest include, but are not limited to, the following:

  • Techniques for handling noisy, corrupted, or incomplete labels in supervised learning;
  • Robust training strategies, loss functions, and regularization methods for DNNs;
  • Metadata-guided, semi-supervised, and weakly supervised approaches to improve model reliability;
  • Adversarial robustness, uncertainty quantification, and generalization under distribution shifts;
  • Applications in natural language processing (NLP), computer vision, bioinformatics, healthcare, and other real-world scenarios;
  • Hybrid or ensemble methods, explainable AI, and interpretable deep learning models;
  • Methods for generating realistic synthetic datasets to address Non-IID and out-of-distribution (OOD) spatiotemporal data, particularly for dynamic environments such as IoT, sensor networks, and cyber-physical systems.

This Special Issue encourages contributions integrating theoretical advancements, algorithmic innovations, and practical implementations to address the challenges posed by imperfect, complex, or non-stationary datasets. It provides a platform for researchers and practitioners to share insights, methods, and solutions that enhance the robustness, reliability, and real-world applicability of neural network systems.

Prof. Dr. Xue Li
Guest Editor

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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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

  • robust deep learning
  • noisy and incomplete data
  • uncertainty quantification
  • generalization and distribution shift
  • explainable and reliable AI

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (1 paper)

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

Review

26 pages, 738 KB  
Review
Analyzing Bias in LLM-Augmented Knowledge Graph Systems: Taxonomy, Interaction Mechanisms, and Evaluation
by Paria Zabihi, Dina Nawara, Ahmed Ibrahim and Rasha Kashef
Appl. Sci. 2026, 16(7), 3410; https://doi.org/10.3390/app16073410 - 1 Apr 2026
Viewed by 1736
Abstract
Large Language Models (LLMs) are increasingly integrated into Knowledge Graph (KG) construction and augmentation pipelines to reduce manual effort and enable scalable knowledge extraction, completion, and reasoning. While this integration offers substantial benefits, it also introduces new forms of bias and unreliability that [...] Read more.
Large Language Models (LLMs) are increasingly integrated into Knowledge Graph (KG) construction and augmentation pipelines to reduce manual effort and enable scalable knowledge extraction, completion, and reasoning. While this integration offers substantial benefits, it also introduces new forms of bias and unreliability that extend beyond those observed in standalone LLMs or traditional knowledge graphs. In particular, biases originating from language models, such as social and representational bias, hallucination, prompt sensitivity, and domain coverage limitations that interact with structural and content biases inherent to knowledge graphs, result in compounded distortions that propagate across the pipeline. This paper provides a structured and comprehensive analysis of bias in LLM-augmented knowledge graph systems. We first review bias mechanisms in LLMs and standalone KGs, and then examine how these biases interact and amplify during key stages of LLM-based entity extraction, relation generation, graph completion, and reasoning. Based on this analysis, we introduce a unified taxonomy that characterizes bias as a pipeline-level phenomenon rather than an isolated model. We further consolidate recent evaluation metrics adapted for LLM-generated graphs, including semantic and soft lexical measures. Additionally, we survey representative datasets and benchmarks used to study bias in LLMs, KGs, and hybrid LLM–KG systems and identify open research gaps in developing pipeline-aware evaluation frameworks. This work aims to support the design of more reliable, accurate, and fair LLM-augmented knowledge graphs for engineering and domain-specific applications. Full article
(This article belongs to the Special Issue Robust and Reliable Neural Networks for Real-World Data)
Show Figures

Figure 1

Back to TopTop