Native Logical and Hierarchical Representations with Subspace Embeddings
Abstract
Traditional neural embeddings represent concepts as points, excelling at similarity but struggling with higher-level reasoning and asymmetric relationships. We introduce a novel paradigm: embedding concepts as linear subspaces. This framework inherently models generality via subspace dimensionality and hierarchy through subspace inclusion. It naturally supports set-theoretic operations like intersection (conjunction), linear sum (disjunction) and orthogonal complements (negations), aligning with classical formal semantics. To enable differentiable learning, we propose a smooth relaxation of orthogonal projection operators, allowing for the learning of both subspace orientation and dimension. Our method achieves state-of-the-art results in reconstruction and link prediction on WordNet. Furthermore, on natural language inference benchmarks, our subspace embeddings surpass bi-encoder baselines, offering an interpretable formulation of entailment that is both geometrically grounded and amenable to logical operations.
Cite
@article{arxiv.2508.16687,
title = {Native Logical and Hierarchical Representations with Subspace Embeddings},
author = {Gabriel Moreira and Zita Marinho and Manuel Marques and João Paulo Costeira and Chenyan Xiong},
journal= {arXiv preprint arXiv:2508.16687},
year = {2025}
}