Data-Centric AI: Tabular Data Synthesis with Deep Generative Models

Preserving logical and functional dependencies in synthetic tabular data

High-quality tabular data is a crucial requirement for developing data-driven applications, especially healthcare-related ones, because most of the data nowadays collected in this context is in tabular form. However, strict data protection laws complicates the access to medical datasets. Thus, synthetic data has become an ideal alternative for data scientists and healthcare professionals to circumvent such hurdles. Although many healthcare institutions still use the classical de-identification and anonymization techniques for generating synthetic data, deep learning-based generative models such as generative adversarial networks (GANs) have shown a remarkable performance in generating tabular datasets with complex structures. This paper examines the GANs’ potential and applicability within the healthcare industry, which often faces serious challenges with insufficient training data and patient records sensitivity. We investigate several state-of-the-art GAN-based models proposed for tabular synthetic data generation. Healthcare datasets with different sizes, numbers of variables, column data types, feature distributions, and inter-variable correlations are examined. Moreover, a comprehensive evaluation framework is defined to evaluate the quality of the synthetic records and the viability of each model in preserving the patients’ privacy. The results indicate that the proposed models can generate synthetic datasets that maintain the statistical characteristics, model compatibility and privacy of the original data. Moreover, synthetic tabular healthcare datasets can be a viable option in many data-driven applications. However, there is still room for further improvements in designing a perfect architecture for generating synthetic tabular data.

Synthetic data offers a promising avenue for addressing privacy, scarcity, and fairness challenges in healthcare datasets. However, there is limited evaluation of how different generation methods balance fidelity, utility, and fairness, particularly for underrepresented subgroups. This study addresses this gap by comparing representative generative modelling techniques, both probabilistic and deep approaches, that are popular in the research literature. We empirically evaluate BayesBoost, CTGAN, TVAE, CopulaGAN, and DECAF on two healthcare datasets containing numerical, binary, and categorical features. Each model’s performance is assessed along three axes: data fidelity, machine learning utility, and fairness, using Accuracy Parity, Equalised Odds, and Predictive Rate Parity. Results show that BayesBoost consistently achieved superior fidelity, utility, and fairness preservation, particularly when paired with Random Forest classifiers, achieving around 60 – 63 % higher downstream utility than GAN-based deep generative baselines (e.g., Random Forest accuracy up to 0.88 with BayesBoost versus 0.54 to − 0.55 for GAN-based methods). Deep generative models, while effective in capturing complex structures, often degraded fairness, especially for underrepresented groups, with equalised odds deviating by over 100 % from the ideal parity value of 1.0 in some settings. The Variational Autoencoder outperformed other deep generative models in fairness preservation, especially for equalised odds, although with some reduction in fidelity and utility. Overall, these findings suggest that synthetic data generation for healthcare must move beyond fidelity evaluations to explicitly assess fairness and subgroup impacts, with probabilistic models such as BayesBoost showing strong potential for ethical deployment, while deep generative models require further adaptation for fairness-sensitive applications.

Automated design synthesis has the potential to revolutionize the modern engineering design process and improve access to highly optimized and customized products across countless industries. Successfully adapting generative machine learning to design engineering may enable such automated design synthesis and is a research subject of great importance. We present a review and analysis of deep generative machine learning models in engineering design. Deep generative models (DGMs) typically leverage deep networks to learn from an input dataset and synthesize new designs. Recently, DGMs such as feedforward neural networks (NNs), generative adversarial networks (GANs), variational autoencoders (VAEs), and certain deep reinforcement learning (DRL) frameworks have shown promising results in design applications like structural optimization, materials design, and shape synthesis. The prevalence of DGMs in engineering design has skyrocketed since 2016. Anticipating the continued growth, we conduct a review of recent advances to benefit researchers interested in DGMs for design. We structure our review as an exposition of the algorithms, datasets, representation methods, and applications commonly used in the current literature. In particular, we discuss key works that have introduced new techniques and methods in DGMs, successfully applied DGMs to a design-related domain, or directly supported the development of DGMs through datasets or auxiliary methods. We further identify key challenges and limitations currently seen in DGMs across design fields, such as design creativity, handling constraints and objectives, and modeling both form and functional performance simultaneously. In our discussion, we identify possible solution pathways as key areas on which to target the future work.

<sec><title>Objective</title> As urban design faces increasing demands for contextual responsiveness, iterative optimization, and data-informed reasoning, integrating artificial intelligence into the design process has gained renewed relevance. Among emerging technologies, generative artificial intelligence (GAI) shows strong potential for automating content creation and simulating spatial configurations. This research provides a comprehensive review of recent developments in the application of GAI to urban design. The research identifies representative technical pathways, their respective intervention stages, and the functional mechanisms by which generative models are reshaping the design workflow. This research presents a structured, theory-informed synthesis of how different generative models contribute to tasks such as intention modeling, spatial reasoning, and performance-driven design. Building on design thinking and a descriptive lens informed by the technology acceptance model (TAM), the research examines how model type, data modality, and task characteristics affect GAI’s functional role, usability, and acceptance. Particular attention is given to mapping deployment forms, from isolated tools to coordinated multi-model workflows, and to characterizing cross-cutting challenges of controllability, transparency, and contextual adaptability in urban design settings. </sec><sec><title>Methods</title> Following the PRISMA protocol, the research conducts a multi-stage literature review combining automated search and expert screening. A total of 125 peer-reviewed articles and high-impact preprints are selected from Web of Science, CNKI, arXiv, and selected industry sources, covering the period from 2014 to July 2025. Search terms such as “generative AI”, “AIGC”, “GAN”, “diffusion model”, “variational autoencoder”, “autoregressive model”, “large language model”, and urban-related keywords are used in various combinations. Based on the collected literature, four types of generative models are summarized as image-driven, language-driven, structure-driven, and feedback-optimized models, according to their application characteristics in urban design tasks. These types are aligned with four stages of the design process: preliminary analysis, scheme generation, evaluation and decision-making, and outcome expression. On this basis, a two-dimensional framework to examine how different GAI pathways intervene across tasks is formed. To refine the mapping, each design stage is further broken down into three representative sub-tasks. Preliminary analysis includes public demand analysis, urban data enhancement, case/task framing, and spatial element recognition. Scheme generation covers design intention modeling, spatial layout generation, and 3D form construction. The evaluation and decision-making stage includes multi-objective optimization, scheme evaluation, and scenario prediction. The final expression stage involves textual documentation, 2D representation, and visual rendering. A quantitative analysis is also conducted to show the distribution of model types over design stages, identify common combinations, and trace the evolution of research focus over time. TAM informs a descriptive synthesis of perceived usefulness (PU) and perceived ease of use (PEU) across model types to illuminate adoption patterns. </sec><sec><title>Results</title> The findings reveal that GAI models are increasingly integrated into urban design workflows but exhibit uneven adoption across task types and modalities. Image-driven models dominate in both early-stage analysis and final visual representation due to their high interpretability, usability, and compatibility with existing design practices. Language-driven models are commonly used in public demand analysis, participatory planning, and scenario scripting, enabled by the rise of large language models (LLMs) such as ChatGPT and DeepSeek. Structure-driven models, though less prevalent, show promise in generating street networks, land-parcel layouts, and spatial typologies using graph-based logic. Feedback-optimized models, which rely on reinforcement learning, evolutionary algorithms, and performance simulation are the least adopted, but demonstrate strong potential in multi-objective optimization and iterative decision-making. Recent research indicates an increasing use of multi-model workflows, such as text-to-image pipelines integrated with urban simulation or feedback loops. While GAI applications increasingly support design iteration, their adoption is heavily influenced by the controllability, explainability, and contextual adaptability of models. PU and PEU vary significantly by model type, with image-driven models rated highest and structure-driven and feedback-optimized models facing usability challenges due to complexity and low transparency. </sec><sec><title>Conclusion</title> Although GAI has demonstrated broad applicability across the urban design process, current implementations are largely procedural and auxiliary in nature. Most models recombine existing inputs rather than construct original logic, and few possess autonomous reasoning or normative awareness. This limits their role to content augmentation rather than conceptual guidance in design development. Moreover, issues such as opaque decision logic, lack of domain-specific knowledge embedding, and poor adaptability to local planning norms hinder practical adoption. Addressing these challenges requires multi-level efforts: 1) Construct structured, regionally grounded urban design datasets; 2) improve model interpretability, controllability, and responsiveness to professional input; and 3) develop modular, multi-model systems that support seamless interaction across design stages. Human – AI collaboration mechanisms — especially those based on iterative prompts and semantic feedback-must be enhanced to enable AI not just as a tool, but as an active design partner. This review offers a comprehensive reference for scholars and practitioners seeking to understand how GAI is reshaping the logic, structure, and agency of urban design. </sec>

While Large Language Models (LLMs) have been increasingly used to generate synthetic data for various downstream tasks, researchers overlook the causal direction in the data synthesis process. A natural causal direction should contain two steps: diverse raw data are generated first, and subsequently annotated for downstream tasks. However, most LLM-based methods adopt an anticausal direction: embedding label information in the prompt to force LLMs to generate targeted data. This reversal raises a critical question: How does the direction of data synthesis impact the quality and utility of the synthetic data? In this work, we empirically study the impact of causal and anticausal data synthesis. To do so, we first design simple yet effective prompting strategies to control the causal direction of LLM-based data synthesis. Using GPT-5 as the data generator, we construct synthetic datasets for three distinct machine learning tasks. We then fine-tune BERT-base and LLaMA-3.2-1B models on these datasets and evaluate them against human-curated benchmarks. Our experiments reveal consistent patterns: (1) models trained on anticausal synthetic data suffer larger performance drops across all tasks and model families --- Accuracy declines range from 13.7%-59.1% for BERT and 4.9%-54.3% for LLaMA, and (2) distributional analysis shows that anticausal synthetic datasets deviate further from human data. Our findings provide practical guidance on how to generate better synthetic data and make good use of it.

This paper presents a comprehensive survey of the applications, challenges, and limitations of Generative AI (GenAI) in enhancing threat intelligence within cybersecurity, supported by real-world case studies. We examine a wide range of data sources in Cyber Threat Intelligence (CTI), including security reports, blogs, social media, network traffic, malware samples, dark web data, and threat intelligence platforms (TIPs). This survey provides a full reference for integrating GenAI into CTI. We discuss various GenAI models such as Large Language Models (LLMs) and Deep Generative Models (DGMs) like Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Diffusion Models, explaining their roles in detecting and addressing complex cyber threats. The survey highlights key applications in areas such as malware detection, network traffic analysis, phishing detection, threat actor attribution, and social engineering defense. We also explore critical challenges in deploying GenAI, including data privacy, security concerns, and the need for interpretable and transparent models. As regulations like the European Commission’s AI Act emerge, ensuring trustworthy AI solutions is becoming more crucial. Real-world case studies, such as the impact of the WannaCry ransomware, the rise of deepfakes, and AI-driven social engineering, demonstrate both the potential and current limitations of GenAI in CTI. Our goal is to provide foundational insights and strategic direction for advancing GenAI’s role in future cybersecurity frameworks, emphasizing the importance of innovation, adaptability, and ongoing learning to enhance resilience against evolving cyber threats. Ultimately, this survey offers critical insights into how GenAI can shape the future of cybersecurity by addressing key challenges and providing actionable guidance for effective implementation.

Generation of realistic synthetic data has garnered considerable attention in recent years, particularly in the health research domain due to its utility in, for instance, sharing data while protecting patient privacy or determining optimal clinical trial design. While much work has been concentrated on synthetic image generation, generation of realistic and complex synthetic tabular data of the type most commonly encountered in classic epidemiological or clinical studies is still lacking, especially with regard to generating data for randomized controlled trials (RCTs). There is no consensus regarding the best way to generate synthetic tabular RCT data such that the underlying multivariate data distribution is preserved. Motivated by an RCT in the treatment of Human Immunodeficiency Virus, we empirically compared the ability of several strategies and three generation techniques (two machine learning, the other a more classical statistical method) to faithfully reproduce realistic data. Our results suggest that using a sequential generation approach with an R-vine copula model to generate baseline variables, followed by a simple random treatment allocation to mimic the RCT setting, and subsequent regression models for variables post-treatment allocation (such as the trial outcome) is the most effective way to generate synthetic tabular RCT data that capture important and realistic features of the real data.

Generative AI models represent a significant advancement in content creation capabilities but face substantial challenges when deployed at the network edge due to inherent resource constraints. This article examines comprehensive optimization strategies for enabling generative AI functionality on edge devices without requiring cloud connectivity. The exponential growth in model size has created a widening gap between computational requirements and the limited resources available in edge environments. Through systematic model compression, architectural redesign, and hardware-software co-optimization, generative models can achieve dramatic efficiency improvements while maintaining acceptable quality thresholds. The compression techniques examined include pruning methodologies that systematically eliminate redundant parameters, quantization approaches that reduce numerical precision, and knowledge distillation methods that transfer capabilities from larger models to compact alternatives. Architectural innovations such as modified attention mechanisms, conditional computation, and neural architecture search further enhance efficiency by fundamentally rethinking model design for resource-constrained environments. The integration of these techniques with hardware-specific optimizations and specialized software frameworks enables practical deployment across diverse application domains. Real-world implementations in speech processing, computer vision, and industrial IoT demonstrate that properly optimized generative models can operate within edge constraints while delivering near-real-time performance and maintaining high-quality outputs. These advancements empower industries to leverage generative AI capabilities in scenarios where privacy concerns, connectivity limitations, or latency requirements make cloud-based processing impractical.

Cyberattack sophistication is rapidly increasing, leading to a decline in the effectiveness of traditional signature-based security solutions. Consequently, intelligent and adaptive security solutions are now being employed that are powered by generative artificial intelligence. Numerous review papers have been conducted on these solutions, but they focus on particular aspects of cybersecurity, providing not a holistic view of all areas. This paper attempts to investigate the applications of generative AI in cyberdefense by reviewing 113 academic papers clustered according to cyberdefense domains indirectly referring to such generative AI models. The review illustrated generative AI’s effectiveness in transferring security from the reactive security model to a proactive one by greatly increasing the detection of new threats and inducing synthetic data which enhances the quality of training, with numerous papers achieving performance accuracy exceeding 95%. There are uniterable issues to overcome however, including the computing costs, model instability and reliance on data. A new multi-dimensional taxonomical methodology and comparative analysis was undertaken on the various generative AI architectures with a strategic roadmap given to guide and orientate further research towards the adoption of autonomous, effective, resilient and reliable cyberdefenses.

This review examines the rapidly expanding landscape of Generative Artificial Intelligence (GenAI) in healthcare, focusing on how models such as GANs, VAEs, diffusion models, and large language models are being explored across medical imaging, clinical documentation, synthetic data generation, drug discovery, and decision-support workflows. Despite GenAI's growing influence, persistent challenges, including limited annotated datasets, concerns over model generalizability, privacy risks, and the opacity of generative architectures, underscore the need for careful evaluation and governance. Accordingly, this study aims to map current applications, assess methodological and ethical constraints, and identify future research opportunities. Using a structured search across ScienceDirect, Scopus, and other sources, the study follows a structured narrative review complemented by quantitative descriptive analysis of the literature. The review also adopts PRISMA-guided screening and standardized data extraction, the review synthesizes evidence from 110 studies published up to October 2025. The findings indicate that the literature frequently reports improvements in imaging quality, data augmentation, molecular modeling workflows, and clinical documentation through generative approaches, particularly in technically constrained settings; however, evidence of clinically validated impact remains uneven across domains. While issues of bias, hallucination, and limited interpretability persist as significant obstacles, imaging-focused applications appear comparatively more mature than decision-support and patient-level modeling tasks. Across domains, diffusion models are commonly associated with higher visual fidelity in biomedical image generation, whereas LLMs demonstrate promise in narrative-oriented tasks but require stronger factual grounding and external verification mechanisms. Overall, the evidence suggests that GenAI’s potential in healthcare is highly context-dependent and contingent upon robust validation frameworks, transparent governance, and human-in-the-loop oversight. The review concludes that responsible integration of GenAI—guided by ethical, legal, and clinical safeguards, will be essential for ensuring safe, equitable, and sustainable adoption in healthcare research, delivery, and policy.

In recent times, slicing methods have yielded a successful outcome in generative models for image, sound, and text data, primarily focusing on joint distributional learning. However, we have identified a critical limitation of the slicing approach for tabular data: it struggles to capture marginal distributional patterns, which are significant for effective tabular data synthesis. To tackle this problem, we introduce a new measure of discrepancy, the mixture Cramer–Wold distance. This measure enables us to capture both marginal and joint distributional patterns simultaneously, striking a balance between the two aspects, and we provide theoretical foundations for its application. Leveraging the power of the mixture Cramer–Wold distance, we present CWDAE (Cramer–Wold Distributional AutoEncoder), a generative model that demonstrates notable performance in generating synthetic tabular data. Furthermore, our model offers the flexibility to adjust the level of data privacy to meet specific needs easily.

Generative AI (GenAI) use is increasing across society in many different industries. Despite widespread adoption in workplaces, there is little consensus on the scope of its benefits and challenges at the level of most industries. Universities are being called upon to equip graduates with important knowledge and skills using GenAI for their professional contexts. Higher education, however, faces issues in effectively and sustainability embedding a use of GenAI in the student experience, which requires adjustments to learning and teaching activities, assessment, and learning outcomes and in access to useful GenAI platforms relevant to the various disciplines. As pedagogical models, ethical debates, and technologies continue to develop in this space, university teachers’ experiences of teaching with GenAI have yet to be explored in detail. Adopting a phenomenographic perspective, this study examines university teachers’ conceptions, perceptions, and approaches to using GenAI in teaching. Leveraging semi-structured interviews with 30 teaching academics, variations of teaching using GenAI were identified. Quantitative analysis was also conducted to capture the associations between these variations. By exploring the qualitative differences between these variations, a nuanced and important contribution to the GenAI discussion from the understanding of university teachers is uncovered. The results show that some ways of understanding and teaching with GenAI are more likely to help students develop effective knowledge and skills for the workplace than others. The findings also offer education leaders evidence to help design effective support for teachers using GenAI to innovate in the student experience. Through investigating the university teacher experience of GenAI, this research adds to the growing debate on the GenAI enabled benefits and challenges that are set to shape the higher education sector.

Data imputation and data generation have important applications across many domains where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful generative models capable of capturing complex data distributions across various data modalities such as image, audio, and time series. Recently, they have been also adapted to generate tabular data. In this article, we propose a diffusion model for tabular data that introduces three key enhancements: (1) a conditioning attention mechanism, (2) an encoder–decoder transformer as the denoising network, and (3) dynamic masking. The conditioning attention mechanism is designed to improve the model’s ability to capture the relationship between the condition and synthetic data. The transformer layers help model interactions within the condition (encoder) or synthetic data (decoder), while dynamic masking enables our model to efficiently handle both missing data imputation and synthetic data generation tasks within a unified framework. We conduct a comprehensive evaluation by comparing the performance of diffusion models with transformer conditioning against state-of-the-art techniques such as Variational Autoencoders, Generative Adversarial Networks, and Diffusion Models, on benchmark datasets. Our evaluation focuses on the assessment of the generated samples with respect to three important criteria, namely: (1) machine learning efficiency, (2) statistical similarity, and (3) privacy risk mitigation. For the task of data imputation, we consider the efficiency of the generated samples across different levels of missing features. The results demonstrate average superior machine learning efficiency and statistical accuracy compared to the baselines, while maintaining privacy risks at a comparable level, particularly showing increased performance in datasets with a large number of features. By conditioning the data generation on a desired target variable, the model can mitigate systemic biases, generate augmented datasets to address data imbalance issues, and improve data quality for subsequent analysis. This has significant implications for domains such as healthcare and finance, where accurate, unbiased, and privacy-preserving data are critical for informed decision-making and fair model outcomes.

While industry practices evolve rapidly, marketing education in Australia and New Zealand faces challenges in keeping pace, particularly regarding the adoption of current marketing technologies (Harrigan et al., 2022). Generative AI, exemplified by systems like ChatGPT and DALL·E, has demonstrated benefits for learning (Baidoo-Anu &amp; Ansah, 2023). However, despite its potential, there remains a dearth of practical guidance on effectively incorporating these technologies into marketing courses. This gap persists even as general frameworks for responsible and ethical AI use, such as the Australian Framework for Generative AI in Schools (2023), emerge. As the demand for graduates with generative AI skills grows in the job market, educators must explore innovative pedagogical approaches to bridge this gap. This academic poster presents an innovative application of generative artificial intelligence (GenAI) in the context of teaching digital marketing at the postgraduate level. Its purpose is to bridge the gap between academic theory and industry practice by encouraging educators to integrate AI tools into their curriculum through experiential learning pedagogy (Kolb, 2014), characterized by a learning process whereby knowledge is created through hands-on experiences. The poster exemplifies how various types of GenAI technologies — specifically text-based, image-based, and video-based — can enhance teaching content, tutorial exercises, and assessments within the digital marketing course. The poster showcases examples of how these GenAI tools are integrated in the course content, to guide students in generating innovative ideas for using AI in marketing to gain a competitive edge: Text-based GenAI: Tools like ChatGPT and Gemini can automatically generate search keywords for search engine marketing. By integrating text-based GenAI tools with established marketing technology (MarTech) tools such as Google Ads and Google Ads Keyword Planner, students engage in practical exercises that combine AI-generated initial ideas (e.g., search keywords) with further analysis (e.g., search volume, click-through rates, and bidding costs) using established MarTech tools. This hands-on approach enhances their learning experience and prepares them for real-world applications. Image-based GenAI: Platforms such as DALL·E, Midjourney, and Stable Diffusion enable the creation of custom images for display advertising, enhancing visual communication in marketing materials. Through experiential learning activities, students can explore ideas, seek unusual combinations, and inspire creativity faster with image-based GenAI tools, resulting in a greater variety of display ad materials. Video-based GenAI: Applications like Sora and Synthesia facilitate the production of short video clips suitable for social media marketing (e.g., YouTube Shorts, TikTok). By engaging in dynamic content creation exercises, students learn to streamline content creation, reduce manual work, and save both time and budget, thereby gaining practical skills in social media marketing. By incorporating these GenAI technologies through experiential learning pedagogy, educators can enrich the learning experience, foster critical thinking, and prepare students for the evolving landscape of digital marketing. Future research can study the use of GenAI in marketing education using theoretical frameworks such as the Unified Theory of Acceptance and Use of Technology (Venkatesh et al., 2016).