# Graph Space Embedding

arXiv: https://arxiv.org/abs/1907.13443 · HTML: https://mlsanity.com/paper/1907.13443/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2019.

## Built on by (most cited first, 2 of 2)

- [Covered Information Disentanglement: Model Transparency via Unbiased Permutation Importance](https://mlsanity.com/paper/2111.09744/) (2021)
- [Interpretable Models via Pairwise permutations algorithm](https://mlsanity.com/paper/2111.09145/) (2021)

## Abstract (arXiv)

We propose the Graph Space Embedding (GSE), a technique that maps the input into a space where interactions are implicitly encoded, with little computations required. We provide theoretical results on an optimal regime for the GSE, namely a feasibility region for its parameters, and demonstrate the experimental relevance of our findings. Next, we introduce a strategy to gain insight on which interactions are responsible for the certain predictions, paving the way for a far more transparent model. In an empirical evaluation on a real-world clinical cohort containing patients with suspected coronary artery disease, the GSE achieves far better performance than traditional algorithms.