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

• URL: http://arxiv.org/abs/2402.14609v4
• Date: Tue, 08 Jul 2025 03:35:45 GMT
• Title: Learning Federated Neural Graph Databases for Answering Complex Queries from Distributed Knowledge Graphs
• Authors: Qi Hu, Weifeng Jiang, Haoran Li, Zihao Wang, Jiaxin Bai, Qianren Mao, Yangqiu Song, Lixin Fan, Jianxin Li,
• Abstract summary: We propose to learn Federated Neural Graph DataBase (FedNGDB), a pioneering systematic framework that empowers privacy-preserving reasoning over multi-source graph data.<n>FedNGDB leverages federated learning to collaboratively learn graph representations across multiple sources, enriching relationships between entities, and improving the overall quality of graph data.
• Score: 53.03085605769093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The increasing demand for deep learning-based foundation models has highlighted the importance of efficient data retrieval mechanisms. Neural graph databases (NGDBs) offer a compelling solution, leveraging neural spaces to store and query graph-structured data, thereby enabling LLMs to access precise and contextually relevant information. However, current NGDBs are constrained to single-graph operation, limiting their capacity to reason across multiple, distributed graphs. Furthermore, the lack of support for multi-source graph data in existing NGDBs hinders their ability to capture the complexity and diversity of real-world data. In many applications, data is distributed across multiple sources, and the ability to reason across these sources is crucial for making informed decisions. This limitation is particularly problematic when dealing with sensitive graph data, as directly sharing and aggregating such data poses significant privacy risks. As a result, many applications that rely on NGDBs are forced to choose between compromising data privacy or sacrificing the ability to reason across multiple graphs. To address these limitations, we propose to learn Federated Neural Graph DataBase (FedNGDB), a pioneering systematic framework that empowers privacy-preserving reasoning over multi-source graph data. FedNGDB leverages federated learning to collaboratively learn graph representations across multiple sources, enriching relationships between entities, and improving the overall quality of graph data.

Related papers

• Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures [50.46688111973999]
  Graph machine learning has led to a significant increase in the capabilities of models that learn on arbitrary graph-structured data.<n>We present a new blueprint that enables end-to-end representation of'relational entity graphs' without traditional engineering feature.<n>We discuss key challenges including large-scale multi-table integration and the complexities of modeling temporal dynamics and heterogeneous data.
  arXiv  Detail & Related papers  (2025-06-19T23:51:38Z)
• Federated Spectral Graph Transformers Meet Neural Ordinary Differential Equations for Non-IID Graphs [3.345437353879255]
  Graph Neural Network (GNN) research is rapidly advancing due to GNNs' capacity to learn distributed representations from graph-structured data.<n>Centralizing large volumes of real-world graph data for GNN training is often impractical due to privacy concerns, regulatory restrictions, and commercial competition.<n>We present a novel method for federated learning on GNNs based on spectral GNNs equipped with neural ordinary differential equations (ODE) for better information capture.
  arXiv  Detail & Related papers  (2025-04-16T06:43:20Z)
• Top Ten Challenges Towards Agentic Neural Graph Databases [56.92578700681306]
  Graph databases (GDBs) like Neo4j and TigerGraph excel at handling interconnected data but lack advanced inference capabilities. This paper introduces Agentic Neural Graph Databases (Agentic NGDBs), which extend NGDBs with three core functionalities.
  arXiv  Detail & Related papers  (2025-01-24T04:06:50Z)
• DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts [70.21017141742763]
  Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. Existing methods generally use a fixed number of GNN layers to generate representations for all graphs. We propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN.
  arXiv  Detail & Related papers  (2024-11-05T11:46:27Z)
• Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networks [16.12856816023414]
  This paper explores the applications and challenges of graph neural networks (GNNs) in processing complex graph data brought about by the rapid development of the Internet. By introducing a self-supervisory mechanism, it is expected to improve the adaptability of existing models to the diversity and complexity of graph data.
  arXiv  Detail & Related papers  (2024-10-23T07:14:37Z)
• LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations [28.77605585519833]
  Graph neural networks, as a popular research area in recent years, have numerous studies on relationship mining. Current cutting-edge research in graph neural networks has not been effectively integrated with large language models. We propose an innovative framework that combines the strong contextual representation capabilities of LLMs with the relationship extraction and analysis functions of GNNs.
  arXiv  Detail & Related papers  (2024-02-14T23:12:09Z)
• Privacy-Preserved Neural Graph Databases [48.57788773216699]
  We propose a privacy-preserved neural graph database (P-NGDB) framework to alleviate the risks of privacy leakage in NGDBs. We introduce adversarial training techniques in the training stage to enforce the NGDBs to generate indistinguishable answers when queried with private information.
  arXiv  Detail & Related papers  (2023-12-25T02:32:05Z)
• Privacy-preserving design of graph neural networks with applications to vertical federated learning [56.74455367682945]
  We present an end-to-end graph representation learning framework called VESPER. VESPER is capable of training high-performance GNN models over both sparse and dense graphs under reasonable privacy budgets.
  arXiv  Detail & Related papers  (2023-10-31T15:34:59Z)
• Learning Representations without Compositional Assumptions [79.12273403390311]
  We propose a data-driven approach that learns feature set dependencies by representing feature sets as graph nodes and their relationships as learnable edges. We also introduce LEGATO, a novel hierarchical graph autoencoder that learns a smaller, latent graph to aggregate information from multiple views dynamically.
  arXiv  Detail & Related papers  (2023-05-31T10:36:10Z)
• Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases [63.96793270418793]
  Complex logical query answering (CLQA) is a recently emerged task of graph machine learning. We introduce the concept of Neural Graph Database (NGDBs) NGDB consists of a Neural Graph Storage and a Neural Graph Engine.
  arXiv  Detail & Related papers  (2023-03-26T04:03:37Z)
• FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphs [22.649780281947837]
  In some practical scenarios, graph data are stored separately in multiple distributed parties, which may not be directly shared due to conflicts of interest. We propose FedEgo, a federated graph learning framework based on ego-graphs to tackle the challenges above.
  arXiv  Detail & Related papers  (2022-08-29T15:47:36Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.