vix.ing · top · new · best · stats

Features-based embedding or Feature-grounding

2025/06/11 by Piotr Makarevich, Makarevich, Piotr
Computer Science · Psychology · #Advanced Graph Neural Networks #Child and Animal Learning Development #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2506.22442

openalex publication_date 2025/06/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In everyday reasoning, when we think about a particular object, we associate it with a unique set of expected properties such as weight, size, or more abstract attributes like density or horsepower. These expectations are shaped by our prior knowledge and the conceptual categories we have formed through experience. This paper investigates how such knowledge-based structured thinking can be reproduced in deep learning models using features based embeddings. Specially, it introduces an specific approach to build feature-grounded embedding, aiming to align shareable representations of operable dictionary with interpretable domain-specific conceptual features.

Citations

Related