DySR: A Dynamic Representation Learning and Aligning based Model for Service Bundle Recommendation

TL;DR

This paper introduces DySR, a dynamic model for service bundle recommendation that accounts for service evolution and representation gaps, significantly improving recommendation accuracy over existing methods.

Contribution

DySR is the first model to incorporate dynamic graph learning and transformation functions to address service evolution and representation gaps in bundle recommendation.

Findings

DySR achieves an F1@5 of 69.3%, outperforming previous methods.

Dynamic graph representation learning improves service requirement matching.

The transformation function effectively aligns service and requirement representations.

Abstract

An increasing number and diversity of services are available, which result in significant challenges to effective reuse service during requirement satisfaction. There have been many service bundle recommendation studies and achieved remarkable results. However, there is still plenty of room for improvement in the performance of these methods. The fundamental problem with these studies is that they ignore the evolution of services over time and the representation gap between services and requirements. In this paper, we propose a dynamic representation learning and aligning based model called DySR to tackle these issues. DySR eliminates the representation gap between services and requirements by learning a transformation function and obtains service representations in an evolving social environment through dynamic graph representation learning. Extensive experiments conducted on a real-world dataset from ProgrammableWeb show that DySR outperforms existing state-of-the-art methods in commonly used evaluation metrics, improving $F1@5$ from $36.1\%$ to $69.3\%$.