2026· International journal of research and innovation in social science· 0 citations
TL;DR
The findings indicate that while modern generative models can produce highly realistic and analytically useful datasets, persistent challenges remain, including the lack of standardized benchmarking protocols, utility–privacy trade-offs, privacy leakage risks, bias amplification, limited explainability, and governance concerns.
Abstract
Generative Artificial Intelligence (GenAI) has transformed data generation through advanced models such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Diffusion Models, and Large Language Models (LLMs), enabling the creation of synthetic datasets that closely resemble real-world data while addressing challenges related to privacy, accessibility, and regulatory compliance. As synthetic data becomes increasingly adopted across healthcare, education, finance, public administration, and social science research, ensuring its quality, reliability, fairness, and trustworthiness has emerged as a critical research priority. This literature review examines recent developments in synthetic data quality evaluation between 2020 and 2026, focusing on key dimensions including utility, fidelity, privacy preservation, fairness, diversity, robustness, interpretability, and governance. The review traces the evolution of evaluation methodologies from traditional statistical similarity measures toward multidimensional assessment frameworks such as SynEval, SynthEval, Benchmarking Synthetic Tabular Data Framework, SynAE, and ESDAE. A structured comparison of these frameworks is presented using criteria including analytical accuracy, scalability, privacy protection, fairness assessment, and interpretability. The review further explores emerging approaches for explainable synthetic data assessment, fairness-aware synthetic data generation, and Privacy-Enhancing Technologies (PETs), including differential privacy, federated learning, secure multi-party computation, and privacy-preserving generative models. In addition, real-world case studies from healthcare, education, public policy, and social science research are examined to demonstrate how synthetic data quality evaluation directly influences decision-making, research validity, and policy outcomes. The findings indicate that while modern generative models can produce highly realistic and analytically useful datasets, persistent challenges remain, including the lack of standardized benchmarking protocols, utility–privacy trade-offs, privacy leakage risks, bias amplification, limited explainability, and governance concerns. The review concludes that future research should prioritize internationally accepted evaluation standards, explainable and fairness-aware assessment frameworks, stronger privacy-preserving mechanisms, and comprehensive governance models to support the responsible, transparent, and trustworthy deployment of synthetic data in the Generative AI era.
The review shows that diffusion and autoregressive foundation models increasingly dominate high-fidelity image, language, and multimodal generation, while GANs, VAEs, and flow-based models remain important in data-limited, structured, scientific, and privacy-aware settings.
A. Javadpour, F. Ja’fari, T. Taleb et al.· IEEE Access· 0 citations
This review examines recent advances and persistent challenges in multi-class classification within machine learning (ML) and deep learning (DL), a core task underpinning many real-world applications in healthcare, finance, social media, and other high-impact domains. The review provides a structured analytical synthesis of major methodological directions, including problem transformation methods, algorithm-level approaches, ensemble and hybrid strategies, class-imbalance handling, evaluation metrics, and deployment-related considerations such as interpretability, uncertainty, and ethics. Recent progress in deep learning architectures, ensemble learning, and active learning has substantially improved predictive accuracy, robustness, and data efficiency across diverse application settings. At the same time, important challenges remain, including imbalanced datasets, noisy labels, scalability constraints, computational cost, and the need for trustworthy and transparent decision-making. The review also examines the trade-offs among predictive performance, interpretability, fairness, and deployment feasibility, highlighting the importance of selecting methods and evaluation metrics that are appropriate to application context. Rather than proposing a new algorithm, this work offers an integrative framework that connects technical advances with practical and ethical considerations in multi-class classification. Finally, it identifies key future directions, including semi-supervised and transfer learning, few-shot and federated multi-class systems, robustness under label noise, energy-efficient model design, and scalable interpretability frameworks for high-stakes deployment.
Y. Qawqzeh, Abdullah Alourani, Fayez Alharbi et al.· PeerJ Computer Science· 0 citations
As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical or legal constraints often limit access to high-quality data. Synthetic data generation can help overcome these limitations. Here, we present a comparative analysis of generative models for transcriptomic data, investigating strategies to incorporate prior biological knowledge via gene graphs. This ensures that synthetic data capture real-world gene patterns, maintaining their usefulness for downstream tasks. In particular, we introduce and benchmark three variants of the Generative Adversarial Network. Among the alternatives, MK-TGAN - an innovative multi-kernel, Graph Neural Network-based model - stands out for its performance in terms of both the realism and utility of the generated data. Unlike other methods, MK-TGAN leverages prior knowledge graphs by exploiting graph neural networks. Our results show that prior knowledge integration strategies improve performance, and that MK-TGAN consistently produces synthetic samples with superior realism and biological plausibility.
Francesca Pia Panaccione, S. Mongardi, M. Masseroli et al.· 0 citations
Data serves as the foundation of contemporary artificial intelligence (AI) systems, yet ethical and practical constraints often limit the availability and usability of real-world datasets. Synthetic data (SD) has emerged as a valuable solution, enabling the development and training of AI models without compromising privacy standards or ethical guidelines. However, many challenges remain to address, from generating high-quality SD using various approaches to investigating the impacts of data training on machine learning (ML) models. This study examines the impact of balancing real and SD and provides some recommendations that researchers can further utilise to improve the ML model’s training process. Three datasets, Mobile Health (MHealth), High-Energy Physics Mass (HEPMass), and US Company Bankruptcy Prediction (UCBP), were pre-processed to ensure compatibility and used as the basis for SD generation using Conditional Tabular Generative Adversarial Networks (CTGAN) and Tabular Variational Autoencoders (TVAE). The study employed a hybrid data generation approach, splitting the training data into varying proportions of real and SD, with performance evaluated through 5-fold cross-validation on Decision Tree (DT), Gaussian Naive Bayes (GNB), and Linear Support Vector (L-SVM) ML models. The results indicate the optimal balance of real and SD for maximising model performance. Analysis of benchmarking results across three datasets shows that combining 30% real data with 70% CTGAN-generated synthetic data achieves the highest accuracy and overall model performance. In contrast, when using TVAE-generated data, a 20% real and 80% synthetic split is recommended to maintain similar performance. Additional experiments conducted on 10% reduced subsets showed that while the primary trends persisted under limited-data conditions, the optimal real-to-synthetic data ratio became more sensitive to the specific dataset. Statistical significance of the model performance differences was further confirmed using paired t-tests across all evaluated mixing ratios. This research analyses these results and considers the state of the art to recommend how further synthetic data can be useful with machine learning models and which approaches to adopt.
Majid Liaquat, Chris D. Nugent, Ian Cleland et al.· IEEE Access· 0 citations
The primary aim of this study is to provide a comprehensive and structured synthesis of existing research to understand how synthetic data is conceptualized, generated, and utilized within educational contexts. By analyzing 29 peer-reviewed articles, the research identifies seven primary dimensions of application: privacy and data sharing, data augmentation, NLP/ text generation, predictive modeling, pedagogical design, methodological analysis, and synthetic data in mobile, interactive, and adaptive learning systems. A significant finding is the increasing integration of artificial intelligence (AI) and machine learning technologies, such as generative adversarial networks (GANs) and large language models (LLMs), which are now central to generating high-fidelity artificial records and augmenting qualitative datasets. Across these analytical, predictive, and pedagogical domains, synthetic data offers a viable response to persistent challenges related to data scarcity, privacy constraints, and limited data accessibility in education. The findings indicate a growing reliance on synthetic generation as an emerging methodological response to data-intensive demands. While synthetic data supports advanced modeling, adaptive learning systems, and instructional design, its epistemological legitimacy and methodological robustness remain contingent on rigorous validation practices. The study concludes that the field currently lacks standardized validation protocols, particularly regarding subgroup equity and fairness. Establishing transparent, equity-aware frameworks remains essential for the future integration of synthetic data into applied educational systems.
Ziyaeddin Halid İpek, Erol Poyraz, Gokhan Yigit· International Journal of Int...· 0 citations
Abstract Background Synthetic data hold substantial potential to address practical challenges in epidemiology due to restricted data access and privacy concerns. However, many current methods suffer from limited quality, high computational demands, and complexity for non-experts. Furthermore, common evaluation strategies for synthetic data often fail to directly reflect statistical utility and measure privacy risks sufficiently. Against this background, a critical underexplored question is whether synthetic data can reliably reproduce key findings from epidemiological research while preserving privacy. Methods We propose adversarial random forests (ARF) as an efficient and convenient method for synthesizing tabular epidemiological data. To evaluate its performance, we replicated statistical analyses from six epidemiological publications covering blood pressure, anthropometry, myocardial infarction, accelerometry, loneliness, and diabetes, from the German National Cohort (NAKO Gesundheitsstudie), the Bremen STEMI Registry U45 Study, and the Guelph Family Health Study. We further assessed how dataset dimensionality and variable complexity affect the quality of synthetic data, and contextualized ARF’s performance by comparison with commonly used tabular data synthesizers in terms of utility, privacy, generalization, and runtime. Results Across all replicated studies, results on ARF-generated synthetic data consistently aligned with original findings. Even for datasets with relatively low sample size-to-dimensionality ratios, replication outcomes closely matched the original results across descriptive and inferential analyses. Reduced dimensionality and variable complexity further enhanced synthesis quality. ARF demonstrated favourable performance regarding utility, privacy preservation, and generalization relative to other synthesizers and superior computational efficiency. Conclusions In summary, ARF reliably generates high-quality synthetic data that replicate diverse epidemiological analyses while offering a competitive privacy–utility trade-off.
J. Kapar, Kathrin Günther, L. Vallis et al.· International Journal of Epi...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
