Siamese Graph Neural Networks for Data Integration
This work addresses the lack of universal automation in data integration, offering a scalable solution for domains like business intelligence, though it is incremental as it builds on existing deep learning techniques.
The paper tackles the problem of automating data integration from structured and unstructured sources by proposing a method that combines siamese and graph neural networks to model entity relations. The result is a system that outperforms rule-based systems and other deep learning approaches on business entity integration tasks.
Data integration has been studied extensively for decades and approached from different angles. However, this domain still remains largely rule-driven and lacks universal automation. Recent development in machine learning and in particular deep learning has opened the way to more general and more efficient solutions to data integration problems. In this work, we propose a general approach to modeling and integrating entities from structured data, such as relational databases, as well as unstructured sources, such as free text from news articles. Our approach is designed to explicitly model and leverage relations between entities, thereby using all available information and preserving as much context as possible. This is achieved by combining siamese and graph neural networks to propagate information between connected entities and support high scalability. We evaluate our method on the task of integrating data about business entities, and we demonstrate that it outperforms standard rule-based systems, as well as other deep learning approaches that do not use graph-based representations.