# TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation

arXiv: https://arxiv.org/abs/2504.17613 · HTML: https://mlsanity.com/paper/2504.17613/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis](https://mlsanity.com/paper/1706.03446/) (2017)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Input Similarity from the Neural Network Perspective](https://mlsanity.com/paper/2102.05262/) (2021)
- [Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification](https://mlsanity.com/paper/2405.19363/) (2024)
- [Vector Quantized Time Series Generation with a Bidirectional Prior Model](https://mlsanity.com/paper/2303.04743/) (2023)
- [MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process](https://mlsanity.com/paper/2403.05751/) (2024)
- [Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Models](https://mlsanity.com/paper/2310.15290/) (2023)
- [TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts](https://mlsanity.com/paper/2501.05403/) (2025)
- [BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling](https://mlsanity.com/paper/2503.02445/) (2025)
- [DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific Information](https://mlsanity.com/paper/2501.05932/) (2025)
- [ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases](https://mlsanity.com/paper/2207.10670/) (2022)
- [Transitioning from Real to Synthetic data: Quantifying the bias in model](https://mlsanity.com/paper/2105.04144/) (2021)
- [PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records](https://mlsanity.com/paper/2307.02006/) (2023)
- [CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models](https://mlsanity.com/paper/2402.13109/) (2024)
- [BioDiffusion: A Versatile Diffusion Model for Biomedical Signal Synthesis](https://mlsanity.com/paper/2401.10282/) (2024)
- [LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction](https://mlsanity.com/paper/2408.12249/) (2024)
- [TimEHR: Image-based Time Series Generation for Electronic Health Records](https://mlsanity.com/paper/2402.06318/) (2024)
- [Controllable Financial Market Generation with Diffusion Guided Meta Agent](https://mlsanity.com/paper/2408.12991/) (2024)
- [PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients' Problems and Data Augmentation with Black-box Large Language Models](https://mlsanity.com/paper/2306.02754/) (2023)
- [Influence Scores at Scale for Efficient Language Data Sampling](https://mlsanity.com/paper/2311.16298/) (2023)
- [InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models](https://mlsanity.com/paper/2412.08480/) (2024)
- [Explicit Temporal Embedding in Deep Generative Latent Models for Longitudinal Medical Image Synthesis](https://mlsanity.com/paper/2301.05465/) (2023)

## Built on by (most cited first, 8 of 8)

- [MIRA: Medical Time Series Foundation Model for Real-World Health Data](https://mlsanity.com/paper/2506.07584/) (2025)
- [TimeFlow: Towards Stochastic-Aware and Efficient Time Series Generation via Flow Matching Modeling](https://mlsanity.com/paper/2511.07968/) (2025)
- [Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations](https://mlsanity.com/paper/2601.13534/) (2026)
- [SOTER: A Generative Time-Series Foundation Model for Wearable Human Physiological Signals](https://mlsanity.com/paper/2609.16804/) (2026)
- [CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records](https://mlsanity.com/paper/2603.23719/) (2026)
- [DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data](https://mlsanity.com/paper/2605.17866/) (2026)
- [FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation](https://mlsanity.com/paper/2605.27892/) (2026)
- [HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling](https://mlsanity.com/paper/2609.34511/) (2026)

## Abstract (arXiv)

Synthetic Electronic Health Record (EHR) time-series generation is crucial for advancing clinical machine learning models, as it helps address data scarcity by providing more training data. However, most existing approaches focus primarily on replicating statistical distributions and temporal dependencies of real-world data. We argue that fidelity to observed data alone does not guarantee better model performance, as common patterns may dominate, limiting the representation of rare but important conditions. This highlights the need for generate synthetic samples to improve performance of specific clinical models to fulfill their target outcomes. To address this, we propose TarDiff, a novel target-oriented diffusion framework that integrates task-specific influence guidance into the synthetic data generation process. Unlike conventional approaches that mimic training data distributions, TarDiff optimizes synthetic samples by quantifying their expected contribution to improving downstream model performance through influence functions. Specifically, we measure the reduction in task-specific loss induced by synthetic samples and embed this influence gradient into the reverse diffusion process, thereby steering the generation towards utility-optimized data. Evaluated on six publicly available EHR datasets, TarDiff achieves state-of-the-art performance, outperforming existing methods by up to 20.4% in AUPRC and 18.4% in AUROC. Our results demonstrate that TarDiff not only preserves temporal fidelity but also enhances downstream model performance, offering a robust solution to data scarcity and class imbalance in healthcare analytics.