Semantic Preserving Embeddings for Generalized Graphs
This work addresses the challenge of semantic data representation in multi-relational machine learning for large relational datasets, but appears incremental as it builds on existing neural encoding and graph topology methods.
The paper tackles the problem of generating vector representations for generalized graphs that preserve semantic characteristics, using neural encoders and topological properties, and tests these representations on machine learning tasks like link discovery and entity retrieval with real datasets.
A new approach to the study of Generalized Graphs as semantic data structures using machine learning techniques is presented. We show how vector representations maintaining semantic characteristics of the original data can be obtained from a given graph using neural encoding architectures and considering the topological properties of the graph. Semantic features of these new representations are tested by using some machine learning tasks and new directions on efficient link discovery, entitity retrieval and long distance query methodologies on large relational datasets are investigated using real datasets. ---- En este trabajo se presenta un nuevo enfoque en el contexto del aprendizaje automático multi-relacional para el estudio de Grafos Generalizados. Se muestra cómo se pueden obtener representaciones vectoriales que mantienen características semánticas del grafo original utilizando codificadores neuronales y considerando las propiedades topológicas del grafo. Además, se evalúan las características semánticas capturadas por estas nuevas representaciones y se investigan nuevas metodologías eficientes relacionadas con Link Discovery, Entity Retrieval y consultas a larga distancia en grandes conjuntos de datos relacionales haciendo uso de bases de datos reales.