HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability

• URL: http://arxiv.org/abs/2512.07988v2
• Date: Wed, 10 Dec 2025 02:59:33 GMT
• Title: HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
• Authors: Sudhanva Manjunath Athreya, Paul Rosen,
• Abstract summary: HOLE (Homological Observation of Latent Embeddings) is a method for analyzing and interpreting deep neural networks through persistent homology.<n>It extracts topological features from neural activations and presents them using a suite of visualization techniques, including Sankey diagrams, heatmaps, dendrograms, and blob graphs.<n>We evaluate HOLE on standard datasets using a range of discriminative models, focusing on representation quality, interpretability across layers, and robustness to input perturbations and model compression.
• Score: 3.1865582949300837
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work introduces HOLE (Homological Observation of Latent Embeddings), a method for analyzing and interpreting deep neural networks through persistent homology. HOLE extracts topological features from neural activations and presents them using a suite of visualization techniques, including Sankey diagrams, heatmaps, dendrograms, and blob graphs. These tools facilitate the examination of representation structure and quality across layers. We evaluate HOLE on standard datasets using a range of discriminative models, focusing on representation quality, interpretability across layers, and robustness to input perturbations and model compression. The results indicate that topological analysis reveals patterns associated with class separation, feature disentanglement, and model robustness, providing a complementary perspective for understanding and improving deep learning systems.

Related papers

• Benchmarking Computational Pathology Foundation Models For Semantic Segmentation [0.0]
  Concatenating features from CONCH, PathDino and CellViT outperformed individual models across all the datasets by 7.95%.<n>We show that the vision language foundation model, CONCH performed the best across datasets when compared to vision-only foundation models.
  arXiv  Detail & Related papers  (2026-02-21T08:00:46Z)
• Cross-View Topology-Aware Graph Representation Learning [0.0]
  We propose GraphTCL, a dual-view contrastive learning framework that integrates structural embeddings from GNNs with topological embeddings derived from persistent homology.<n>Experiments on benchmark datasets, including TU and OGB molecular graphs, demonstrate that GraphTCL consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-12-01T19:00:58Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [60.83579255387347]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• Enhancing Graph Representation Learning with Localized Topological Features [29.562627708301694]
  We propose a principled approach to extract the rich connectivity information of graphs based on the theory of persistent homology.<n>Our method utilizes the topological features to enhance the representation learning of graph neural networks.
  arXiv  Detail & Related papers  (2025-01-15T22:12:27Z)
• TopER: Topological Embeddings in Graph Representation Learning [8.052380377159398]
  Topological Evolution Rate (TopER) is a low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures. Our models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization.
  arXiv  Detail & Related papers  (2024-10-02T17:31:33Z)
• Experimental Observations of the Topology of Convolutional Neural Network Activations [2.4235626091331737]
  Topological data analysis provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification.
  arXiv  Detail & Related papers  (2022-12-01T02:05:44Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [102.9138736545956]
  Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies. In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
  arXiv  Detail & Related papers  (2022-04-30T12:57:02Z)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation [22.688772441351308]
  Methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods provide lower resolution and blurry explanation maps that limit their explanation power. In this work, we collect visualization maps from multiple layers of the model based on an attribution-based input sampling technique. We also propose a layer selection strategy that applies to the whole family of CNN-based models.
  arXiv  Detail & Related papers  (2020-10-01T20:27:30Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification [50.83222170524406]
  We study the intrinsic difficulty in graph classification under the unified concept of resolution dilemmas'' We propose SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling.
  arXiv  Detail & Related papers  (2020-06-29T01:01:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.