Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

Learning Federated Neural Graph Databases for Answering Complex Queries from Distributed Knowledge Graphs

Created by
  • Haebom

Author

Qi Hu, Weifeng Jiang, Haoran Li, Zihao Wang, Jiaxin Bai, Qianren Mao, Yangqiu Song, Lixin Fan, Jianxin Li

Outline

This paper emphasizes the importance of efficient data retrieval mechanisms in response to the increasing demand for deep learning-based foundational models, and neural graph databases (NGDBs) are proposed as a solution. NGDBs utilize neural space to store and query graph-structured data, allowing LLMs to access accurate and contextually relevant information. However, existing NGDBs are limited to single-graph operations, have limited ability to infer across multiple distributed graphs, and do not support multi-source graph data, making it difficult to capture the complexity and diversity of real-world data. For sensitive graph data, direct sharing and aggregation pose significant privacy risks. Therefore, in this paper, we propose FedNGDB (Federated Neural Graph DataBase), a groundbreaking system framework that enables privacy-preserving inference on graph data from multiple sources. FedNGDB jointly learns graph representations from multiple sources using federated learning to enrich relationships between entities and improve the overall quality of graph data.

Takeaways, Limitations

•
Takeaways:
◦
We present a FedNGDB framework that enables privacy-preserving inference on multi-source graph data.
◦
Efficiently learning graph representations from multiple sources via federated learning.
◦
Enriching relationships between entities and improving graph data quality.
◦
Solves the problems of single graph operations and lack of multi-source data support in existing NGDBs.
•
Limitations:
◦
Lack of experimental evaluation of the performance and efficiency of FedNGDB.
◦
Lack of validation of applicability to various types of graph data and real-world applications.
◦
Due to the nature of federated learning, there is a possibility of data imbalance or communication overhead problems.
👍
Made with Slashpage