# DANIEL: A Distributed and Scalable Approach for Global Representation Learning with EHR Applications

arXiv: https://arxiv.org/abs/2511.02754 · HTML: https://mlsanity.com/paper/2511.02754/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 147 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 12 of 12)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [BIOS: An Algorithmically Generated Biomedical Knowledge Graph](https://mlsanity.com/paper/2203.09975/) (2022)
- [Performance Analysis and Comparison of Distributed Machine Learning Systems](https://mlsanity.com/paper/1909.02061/) (2019)
- [A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments](https://mlsanity.com/paper/2502.16065/) (2025)
- [Representation learning to advance multi-institutional studies with electronic health record data from US and France](https://mlsanity.com/paper/2502.08547/) (2025)
- [Representation-Enhanced Neural Knowledge Integration with Application to Large-Scale Medical Ontology Learning](https://mlsanity.com/paper/2410.07454/) (2024)
- [Medical Profile Model: Scientific and Practical Applications in Healthcare](https://mlsanity.com/paper/2107.03913/) (2021)
- [Likelihood Based Inference in Fully and Partially Observed Exponential Family Graphical Models with Intractable Normalizing Constants](https://mlsanity.com/paper/2404.17763/) (2024)
- [Unsupervised Ensemble Learning via Ising Model Approximation with Application to Phenotyping Prediction](https://mlsanity.com/paper/1810.06376/) (2018)
- [Reconstruct Ising Model with Global Optimality via SLIDE](https://mlsanity.com/paper/2310.09257/) (2023)
- [BernGraph: Probabilistic Graph Neural Networks for EHR-based Medication Recommendations](https://mlsanity.com/paper/2408.09410/) (2024)

## Abstract (arXiv)

Classical probabilistic graphical models face fundamental challenges in modern data environments, which are characterized by high dimensionality, source heterogeneity, and stringent data-sharing constraints. In this work, we revisit the Ising model, a well-established member of the Markov Random Field (MRF) family, and develop a distributed framework that enables scalable and privacy-preserving representation learning from large-scale binary data with inherent low-rank structure. Our approach optimizes a non-convex surrogate loss function via bi-factored gradient descent, offering substantial computational and communication advantages over conventional convex approaches. We evaluate our algorithm on multi-institutional electronic health record (EHR) datasets from 58,248 patients across the University of Pittsburgh Medical Center (UPMC) and Mass General Brigham (MGB), demonstrating superior performance in global representation learning and downstream clinical tasks, including relationship detection, patient phenotyping, and patient clustering. These results highlight a broader potential for statistical inference in federated, high-dimensional settings while addressing the practical challenges of data complexity and multi-institutional integration.