A Survey of Reasoning for Substitution Relationships: Definitions, Methods, and Directions
Anxin Yang, Zhijuan Du, Tao Sun
TL;DR
This paper surveys reasoning for substitution relationships across domains, focusing on definitions, representations, learning, and reasoning methods. It proposes a framework organizing data preprocessing, feature representation, relation learning and inference, training, and evaluation. It reviews available datasets and evaluation criteria, and discusses challenges such as interpretability and data sparsity. It outlines future directions including multimodal and multilevel modeling, temporality, and integration with large language models to improve personalization and accuracy.
Abstract
Substitute relationships are fundamental to people's daily lives across various domains. This study aims to comprehend and predict substitute relationships among products in diverse fields, extensively analyzing the application of machine learning algorithms, natural language processing, and other technologies. By comparing model methodologies across different domains, such as defining substitutes, representing and learning substitute relationships, and substitute reasoning, this study offers a methodological foundation for delving deeper into substitute relationships. Through ongoing research and innovation, we can further refine the personalization and accuracy of substitute recommendation systems, thus advancing the development and application of this field.