</> Code with Papers by Syntology

Papers › Interpretable Visualizations with Differentiating Embedding Networks

Interpretable Visualizations with Differentiating Embedding Networks

11 Jun 2020arXiv:2006.06640archive 2025-07-28

Isaac Robinson

We present a visualization algorithm based on a novel unsupervised Siamese neural network training regime and loss function, called Differentiating Embedding Networks (DEN). The Siamese neural network finds differentiating or similar features between specific pairs of samples in a dataset, and uses these features to embed the dataset in a lower dimensional space where it can be visualized. Unlike existing visualization algorithms such as UMAP or t-SNE, DEN is parametric, meaning it can be interpreted by techniques such as SHAP. To interpret DEN, we create an end-to-end parametric clustering algorithm on top of the visualization, and then leverage SHAP scores to determine which features in the sample space are important for understanding the structures shown in the visualization based on the clusters found. We compare DEN visualizations with existing techniques on a variety of datasets, including image and scRNA-seq data. We then show that our clustering algorithm performs similarly to the state of the art despite not having prior knowledge of the number of clusters, and sets a new state of the art on FashionMNIST. Finally, we demonstrate finding differentiating features of a dataset. Code available at https://github.com/isaacrob/DEN

PaperPDFCode

Code

isaacrob/DEN officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClusteringImage Clustering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering Fashion-MNIST DEN Accuracy 0.635 #6 of 13 Archive leaderboard report
Image Clustering Fashion-MNIST DEN NMI 0.71 #6 of 13 Archive leaderboard report
Image Clustering MNIST-full DEN Accuracy 0.984 #6 of 16 Archive leaderboard report
Image Clustering MNIST-full DEN NMI 0.956 #6 of 16 Archive leaderboard report
Image Clustering USPS DEN Accuracy 0.979 #3 of 16 Archive leaderboard report
Image Clustering USPS DEN NMI 0.944 #3 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SHAP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections