# Knowledge-Embedded Latent Projection for Robust Representation Learning

arXiv: https://arxiv.org/abs/2602.16709 · HTML: https://mlsanity.com/paper/2602.16709/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare](https://mlsanity.com/paper/1810.09593/) (2018)
- [Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably](https://mlsanity.com/paper/1606.03168/) (2016)
- [Spherical Regression under Mismatch Corruption with Application to Automated Knowledge Translation](https://mlsanity.com/paper/1810.05679/) (2018)
- [On Cross-validation for Sparse Reduced Rank Regression](https://mlsanity.com/paper/1812.11555/) (2018)
- [Representation-Enhanced Neural Knowledge Integration with Application to Large-Scale Medical Ontology Learning](https://mlsanity.com/paper/2410.07454/) (2024)
- [A General Latent Embedding Approach for Modeling Non-uniform High-dimensional Sparse Hypergraphs with Multiplicity](https://mlsanity.com/paper/2410.12108/) (2024)

## Built on by (most cited first, 1 of 1)

- [LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model](https://mlsanity.com/paper/2608.22295/) (2026)

## Abstract (arXiv)

Latent space models are widely used for analyzing high-dimensional discrete data matrices, such as patient-feature matrices in electronic health records (EHRs), by capturing complex dependence structures through low-dimensional embeddings. However, estimation becomes challenging in the imbalanced regime, where one matrix dimension is much larger than the other. In EHR applications, cohort sizes are often limited by disease prevalence or data availability, whereas the feature space remains extremely large due to the breadth of medical coding system. Motivated by the increasing availability of external semantic embeddings, such as pre-trained embeddings of clinical concepts in EHRs, we propose a knowledge-embedded latent projection model that leverages semantic side information to regularize representation learning. Specifically, we model column embeddings as smooth functions of semantic embeddings via a mapping in a reproducing kernel Hilbert space. We develop a computationally efficient two-step estimation procedure that combines semantically guided subspace construction via kernel principal component analysis with scalable projected gradient descent. We establish estimation error bounds that characterize the trade-off between statistical error and approximation error induced by the kernel projection. Furthermore, we provide local convergence guarantees for our non-convex optimization procedure. Extensive simulation studies and a real-world EHR application demonstrate the effectiveness of the proposed method.