Special Session 1: Using Knowledge Graph in Learning Algorithms

Description: Learning algorithms perform several tasks, including modeling with knowledge graphs and embedding these graphs into low-dimensional vector spaces. These embeddings can then be utilized by standard machine learning models for various purposes, such as classification, clustering, recommendation, prediction, and tackling new graph neural network tasks.
In modern machine learning, knowledge graphs serve as a bridge between symbolic knowledge representation and data-driven learning, allowing algorithms to exploit both structured domain knowledge and statistical patterns.

Session organizer:
Prof. Guillermo De Ita Luna, Autonomous University of Puebla (BUAP), México

The topics of interest include, but are not limited to:
▪ Recommendation systems
▪ Natural language processing
▪ Question answering systems
▪ Biomedical informatics
▪ Social network analysis
▪ Fraud detection

Submission method:
Submit your Full Paper or your paper abstract-without publication (200-400 words) via Online Submission System, then choose Special Session 1 (Using Knowledge Graph in Learning Algorithms)
Template Download

Introduction of session organizer:

Prof. Guillermo De Ita Luna
Autonomous University of Puebla (BUAP), México

Guillermo De Ita Luna has made research stances in Texas A&M, Chicago University, Lille – Inria France, and in several Universities in Mexico. 34 years as a Full Professor and researcher in the Computer Sc. Faculty at the Autonomous University of Puebla (BUAP), México. He was the principal from that faculty from 1999 to 2003. Currently, he is a member of the Mexican System of Researchers at level 3 (the highest level). He has supervised 59 thesis projects; 32 in bachelor ‘s level and 23 in posgrade level. He has published 140 research articles in journals and conference proceedings that underwent rigorous double-blind peer review, along with 30 book chapters. Additionally, he contributed as an author to the publication of 5 books.