# Visualizing the PHATE of Neural Networks

arXiv: https://arxiv.org/abs/1908.02831 · HTML: https://mlsanity.com/paper/1908.02831/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2019.

## Built on by (most cited first, 18 of 18)

- [Reliability of CKA as a Similarity Measure in Deep Learning](https://mlsanity.com/paper/2210.16156/) (2022)
- [Neural population geometry: An approach for understanding biological and artificial neural networks](https://mlsanity.com/paper/2104.07059/) (2021)
- [Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models](https://mlsanity.com/paper/2104.07578/) (2021)
- [Learning shared neural manifolds from multi-subject FMRI data](https://mlsanity.com/paper/2201.00622/) (2021)
- [Diffusion Curvature for Estimating Local Curvature in High Dimensional Data](https://mlsanity.com/paper/2206.03977/) (2022)
- [Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings](https://mlsanity.com/paper/2505.15353/) (2025)
- [Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors](https://mlsanity.com/paper/2210.01760/) (2022)
- [Generating Attribution Maps with Disentangled Masked Backpropagation](https://mlsanity.com/paper/2101.06773/) (2021)
- [Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Training](https://mlsanity.com/paper/2406.01969/) (2024)
- [Unsupervised discovery of the shared and private geometry in multi-view data](https://mlsanity.com/paper/2408.12091/) (2024)
- [On the Evolution of Neuron Communities in a Deep Learning Architecture](https://mlsanity.com/paper/2106.04693/) (2021)
- [Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning](https://mlsanity.com/paper/2202.06781/) (2022)
- [A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks](https://mlsanity.com/paper/2307.07575/) (2023)
- [Neural Surveillance: Live-Update Visualization of Latent Training Dynamics](https://mlsanity.com/paper/2405.15135/) (2024)
- [Noisy Data Visualization using Functional Data Analysis](https://mlsanity.com/paper/2406.03396/) (2024)
- [Domain-Adversarial Neural Network and Explainable AI for Reducing Tissue-of-Origin Signal in Pan-cancer Mortality Classification](https://mlsanity.com/paper/2504.10343/) (2025)
- [Neighbor Embedding for High-Dimensional Sparse Poisson Data](https://mlsanity.com/paper/2604.16932/) (2026)
- [From Layers to Networks: Comparing Neural Representations via Diffusion Geometry](https://mlsanity.com/paper/2605.15901/) (2026)

## Abstract (arXiv)

Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduce a novel visualization algorithm that reveals the internal geometry of such networks: Multislice PHATE (M-PHATE), the first method designed explicitly to visualize how a neural network's hidden representations of data evolve throughout the course of training. We demonstrate that our visualization provides intuitive, detailed summaries of the learning dynamics beyond simple global measures (i.e., validation loss and accuracy), without the need to access validation data. Furthermore, M-PHATE better captures both the dynamics and community structure of the hidden units as compared to visualization based on standard dimensionality reduction methods (e.g., ISOMAP, t-SNE). We demonstrate M-PHATE with two vignettes: continual learning and generalization. In the former, the M-PHATE visualizations display the mechanism of "catastrophic forgetting" which is a major challenge for learning in task-switching contexts. In the latter, our visualizations reveal how increased heterogeneity among hidden units correlates with improved generalization performance. An implementation of M-PHATE, along with scripts to reproduce the figures in this paper, is available at https://github.com/scottgigante/M-PHATE.