Skip to content
AI News HubLIVE
Original source2 min read

ProToMEx: Rapid, Interpretable Explanations via Structured Representations

Summary

ProToMEx is a model-agnostic explainability framework that uses probabilistic topic models to learn latent 'topics' as high-level reasons for classifier decisions. It provides both global and local explanations, matches SHAP and LIME in fidelity, and generates local explanations about 30–40x faster on standardized tabular and synthetic datasets.

SourcearXiv Machine LearningAuthor: Athina Georgara, Adarsh Valoor, Sarvapali D. Ramchurn
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:ProToMEx: Rapid, Interpretable Explanations via Structured Representations

View a PDF of the paper titled ProToMEx: Rapid, Interpretable Explanations via Structured Representations, by Athina Georgara and 2 other authors

View PDF HTML (experimental)

Abstract:Existing post-hoc explainers for machine learning classifiers primarily focus on feature attribution, assigning importance scores to individual features. While valuable, this approach struggles to articulate the complex, combinatorial patterns that often drive a model's decision-making process. To overcome this limitation, we introduce ProToMEx, a new paradigm for explainability that leverages Probabilistic Topic Models (PTMs). Our model-agnostic framework learns latent ''topics'' that represent distinct, high-level reasons for a classification, moving beyond simple feature importance to reveal underlying semantic structures. ProToMEx naturally provides both global explanations of a model's overall behaviour and local explanations that can disentangle multiple co-existing reasons for a specific prediction. We demonstrate empirically that ProToMEx not only produces explanations of comparable fidelity to popular methods like SHAP and LIME but also drastically reduces the amortised computational cost of generating local explanations, making it highly suitable for real-time applications. Specifically, we show that ProToMEx is ~30-40x faster than SHAP and LIME over standardised tabular datasets and synthetic datasets.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2609.04265 [cs.LG]

(or arXiv:2609.04265v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.04265

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Athina Georgara [view email] [v1] Wed, 2 Sep 2026 18:39:29 UTC (71 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled ProToMEx: Rapid, Interpretable Explanations via Structured Representations, by Athina Georgara and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • ProToMEx applies probabilistic topic models to model-agnostic explainability, learning latent topics that capture high-level reasons behind classifications.
  • It supports both global explanations of model behavior and local explanations that separate multiple coexisting causes for a single prediction.
  • Empirical results show explanation fidelity on par with SHAP and LIME while reducing the amortized cost of local explanations by roughly 30–40x over standardized tabular and synthetic datasets.

Highlights and analysis are generated automatically and may contain errors. Check the original source.