LAVA: Explainability for Unsupervised Latent Embeddings

• URL: http://arxiv.org/abs/2509.21149v1
• Date: Thu, 25 Sep 2025 13:38:17 GMT
• Title: LAVA: Explainability for Unsupervised Latent Embeddings
• Authors: Ivan Stresec, Joana P. Gonçalves,
• Abstract summary: Locality-Aware Variable Associations (LAVA) is designed to explain local embedding organization through its relationship with the input features.<n>Based on UMAP embeddings of MNIST and a single-cell kidney dataset, we show that LAVA captures relevant feature associations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Unsupervised black-box models can be drivers of scientific discovery, but remain difficult to interpret. Crucially, discovery hinges on understanding the model output, which is often a multi-dimensional latent embedding rather than a well-defined target. While explainability for supervised learning usually seeks to uncover how input features are used to predict a target, its unsupervised counterpart should relate input features to the structure of the learned latent space. Adaptations of supervised model explainability for unsupervised learning provide either single-sample or dataset-wide summary explanations. However, without automated strategies of relating similar samples to one another guided by their latent proximity, explanations remain either too fine-grained or too reductive to be meaningful. This is especially relevant for manifold learning methods that produce no mapping function, leaving us only with the relative spatial organization of their embeddings. We introduce Locality-Aware Variable Associations (LAVA), a post-hoc model-agnostic method designed to explain local embedding organization through its relationship with the input features. To achieve this, LAVA represents the latent space as a series of localities (neighborhoods) described in terms of correlations between the original features, and then reveals reoccurring patterns of correlations across the entire latent space. Based on UMAP embeddings of MNIST and a single-cell kidney dataset, we show that LAVA captures relevant feature associations, with visually and biologically relevant local patterns shared among seemingly distant regions of the latent spaces.

Related papers

• AlignSAE: Concept-Aligned Sparse Autoencoders [47.18866175760984]
  We introduce AlignSAE, a method that aligns SAE features with a defined ontology through a "pre-train, then post-train" curriculum.<n>After an initial unsupervised training phase, we apply supervised post-training to bind specific concepts to dedicated latent slots.<n>This separation creates an interpretable interface where specific relations can be inspected and controlled without interference from unrelated features.
  arXiv  Detail & Related papers  (2025-12-01T18:58:22Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [64.74977204942199]
  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)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts [3.9426000822656224]
  We conjecture that in large language models, the embeddings live in a local manifold structure with different dimensions depending on the perplexities and domains of the input data.<n>By incorporating an attention-based soft-gating network, we verify that our model learns specialized sub-manifolds for an ensemble of input data sources.
  arXiv  Detail & Related papers  (2025-02-19T09:33:16Z)
• Querying functional and structural niches on spatial transcriptomics data [7.240034062898855]
  spatial transcriptomics enables gene expression profiling in spatial contexts.<n>It has been revealed that spatial niches serve as cohesive and recurrent units in physiological and pathological processes.<n>We defined the Niche Query Task, which is to identify similar niches across ST samples given a niche of interest (NOI)<n>We developed QueST, a specialized method for solving this task.
  arXiv  Detail & Related papers  (2024-10-14T16:01:27Z)
• Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data [3.376269351435396]
  We develop a formal perspective on probing using structural causal models (SCM) We extend a recent study of LMs in the context of a synthetic grid-world navigation task. Our techniques provide robust empirical evidence for the ability of LMs to induce the latent concepts underlying text.
  arXiv  Detail & Related papers  (2024-07-18T17:59:27Z)
• Towards Statistically Significant Taxonomy Aware Co-location Pattern Detection [4.095979270829907]
  The goal is to find subsets of feature types or their parents whose spatial interaction is statistically significant. The problem is computationally challenging due to the exponential number of candidate co-location patterns generated by the taxonomy. This paper introduces two methods for incorporating and assessing the statistical significance of co-location patterns.
  arXiv  Detail & Related papers  (2024-06-29T04:48:39Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• Discovering Class-Specific GAN Controls for Semantic Image Synthesis [73.91655061467988]
  We propose a novel method for finding spatially disentangled class-specific directions in the latent space of pretrained SIS models. We show that the latent directions found by our method can effectively control the local appearance of semantic classes.
  arXiv  Detail & Related papers  (2022-12-02T21:39:26Z)
• When are Post-hoc Conceptual Explanations Identifiable? [18.85180188353977]
  When no human concept labels are available, concept discovery methods search trained embedding spaces for interpretable concepts. We argue that concept discovery should be identifiable, meaning that a number of known concepts can be provably recovered to guarantee reliability of the explanations. Our results highlight the strict conditions under which reliable concept discovery without human labels can be guaranteed.
  arXiv  Detail & Related papers  (2022-06-28T10:21:17Z)
• Encoding Domain Information with Sparse Priors for Inferring Explainable Latent Variables [2.8935588665357077]
  We propose spex-LVM, a factorial latent variable model with sparse priors to encourage the inference of explainable factors. spex-LVM utilizes existing knowledge of curated biomedical pathways to automatically assign annotated attributes to latent factors. Evaluations on simulated and real single-cell RNA-seq datasets demonstrate that our model robustly identifies relevant structure in an inherently explainable manner.
  arXiv  Detail & Related papers  (2021-07-08T10:19:32Z)
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation [51.083573770706636]
  This work uses relational inference to fill in the incomplete data. We propose Omni-Relational Network (OR-Net) to model the pointwise relativity in two aspects.
  arXiv  Detail & Related papers  (2021-05-02T06:05:54Z)
• Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
  A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
  arXiv  Detail & Related papers  (2020-07-13T18:05:36Z)

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.