Bridging Logic and Learning: Decoding Temporal Logic Embeddings via Transformers
Jul 10, 2025·
·
1 min read
Sara Candussio
Image credit: UnsplashAbstract
Continuous representations of logic formulae allow integration of symbolic knowledge into data-driven learning algorithms. If such embeddings are semantically consistent, they enable learning and optimization directly in the semantic space. We train a Transformer-based decoder to invert embeddings of Signal Temporal Logic (STL) formulae. Our model generates valid formulae after 1 epoch and generalizes semantic understanding in about 10 epochs. Decoded formulae are often simpler yet semantically equivalent to references. We evaluate performance across formula complexity levels and deploy the model for requirement mining tasks, performing optimization directly in semantic space.
Type
Publication
ECML-PKDD 2025
This work introduces a Transformer-based decoder that inverts embeddings of Signal Temporal Logic (STL) formulae. By constructing a small STL vocabulary, the model can generate valid formulae quickly, generalize across semantic structures, and simplify formulas while preserving their meaning. Our methodology is evaluated across varying formula complexity and applied to requirement mining tasks, performing optimization directly in the semantic space.
Create your slides in Markdown - click the Slides button to check out the example.
Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.
If you find overlap with your work or interests, I would be glad to connect and explore possible collaborations.
