A Systematic Review of Federated Generative Models

AV Gargary, E De Cristofaro - arxiv preprint arxiv:2405.16682, 2024 - arxiv.org
Federated Learning (FL) has emerged as a solution for distributed systems that allow clients
to train models on their data and only share models instead of local data. Generative Models …

Tabular data synthesis with differential privacy: A survey

M Yang, CH Chi, KY Lam, J Feng, T Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
Data sharing is a prerequisite for collaborative innovation, enabling organizations to
leverage diverse datasets for deeper insights. In real-world applications like FinTech and …

Imb-FinDiff: Conditional Diffusion Models for Class Imbalance Synthesis of Financial Tabular Data

M Schreyer, T Sattarov, A Sim, K Wu - Proceedings of the 5th ACM …, 2024 - dl.acm.org
Handling imbalanced datasets remains a critical challenge in financial machine-learning
applications such as loan approval, credit scoring, and fraud detection. We present …

Differentially Private Federated Learning of Diffusion Models for Synthetic Tabular Data Generation

T Sattarov, M Schreyer, D Borth - arxiv preprint arxiv:2412.16083, 2024 - arxiv.org
The increasing demand for privacy-preserving data analytics in finance necessitates
solutions for synthetic data generation that rigorously uphold privacy standards. We …

Limitations and Improvements of Evaluation Metrics for Relational Tabular Synthetic Data

SB Lee, H Bae - Annual Conference of KIPS, 2024 - koreascience.kr
합성데이터는 통계적 특성이 유사한 가상의 데이터로, 개인정보 보호 및 데이터 부족 문제를
해결하는 데 기여한다. 이를 관계형 데이터베이스로 확장한 관계형 테이블 합성데이터는 금융 …