# LatentFlow: Visual Analytics for Latent Space Analysis in Molecular Graph Neural Networks

arXiv: https://arxiv.org/abs/2607.21941 · HTML: https://mlsanity.com/paper/2607.21941/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 59 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Directional Message Passing for Molecular Graphs](https://mlsanity.com/paper/2003.03123/) (2020)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [Emergence of Invariance and Disentanglement in Deep Representations](https://mlsanity.com/paper/1706.01350/) (2017)
- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Geometric Deep Learning on Molecular Representations](https://mlsanity.com/paper/2107.12375/) (2021)
- [Embedding Projector: Interactive Visualization and Interpretation of Embeddings](https://mlsanity.com/paper/1611.05469/) (2016)
- [Understanding Collapse in Non-Contrastive Siamese Representation Learning](https://mlsanity.com/paper/2209.15007/) (2022)
- [WizMap: Scalable Interactive Visualization for Exploring Large Machine Learning Embeddings](https://mlsanity.com/paper/2306.09328/) (2023)
- [EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection](https://mlsanity.com/paper/1808.09074/) (2018)
- [DimReader: Axis lines that explain non-linear projections](https://mlsanity.com/paper/1710.00992/) (2017)
- [Deep Learning Foundation Models from Classical Molecular Descriptors](https://mlsanity.com/paper/2506.15792/) (2025)
- [Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees](https://mlsanity.com/paper/1908.10410/) (2019)
- [Visualizing Graph Neural Networks with CorGIE: Corresponding a Graph to Its Embedding](https://mlsanity.com/paper/2106.12839/) (2021)
- [ChemVA: Interactive Visual Analysis of Chemical Compound Similarity in Virtual Screening](https://mlsanity.com/paper/2008.13150/) (2020)

## Abstract (arXiv)

Chemists and materials scientists increasingly use machine learning models, such as graph neural networks (GNNs), to predict properties of molecules and the outcomes of their reactions. Beyond predictive performance, understanding how these models organize chemical information internally in their latent spaces, i.e., the embeddings of the molecules, is critical. Analyzing latent spaces helps diagnose model behavior and assess whether the learned embeddings are organized in ways that reflect meaningful chemical relationships. Unfortunately, existing methods provide limited support for analyzing latent spaces across layers and across different model states (e.g., training epochs, model configurations, and input data), making it difficult to understand how these latent spaces evolve throughout a model or relate to chemical concepts. We present LatentFlow, a visual analytics system developed in collaboration with a domain expert for analyzing latent spaces in molecular GNNs. LatentFlow groups embeddings into clusters and supports exploration of latent spaces by tracking how these clusters change across layers and model states using a modified Sankey diagram. To support interpretation, LatentFlow links these clusters to representative molecules and their shared substructures, and it allows scientists to introduce their own domain knowledge and compare it with the patterns found in the latent spaces. We evaluate LatentFlow through two case studies. The results show that LatentFlow helps scientists understand how latent spaces evolve, identify meaningful molecular patterns, and better interpret model behavior.