Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Knowledge Graphs-Driven Intelligence for Distributed Decision Systems

Rosario Napoli, Gabriele Morabito, Antonio Celesti, Massimo Villari, Maria Fazio

TL;DR

The paper tackles the challenge of decentralized coordination in data-heterogeneous, dynamic distributed systems. It introduces Knowledge Sharing, a paradigm that combines Knowledge Graphs with Graph Embeddings (via GraphSAGE) to produce a Knowledge Map as a global semantic abstraction, without centralized control, across a 4-layer architecture (Physical, Storage, Knowledge, Decision). The authors provide formal KG/GE definitions and a detailed workflow for local/global embedding propagation, culminating in a dynamic Knowledge Map that guides autonomous decisions. Preliminary experiments on distributed service orchestration across varied topologies demonstrate the approach's ability to maintain semantic coherence and adaptability in edge, IoT, and multi-agent environments.

Abstract

Modern distributed decision-making systems face significant challenges arising from data heterogeneity, dynamic environments, and the need for decentralized coordination. This paper introduces the Knowledge Sharing paradigm as an innovative approach that uses the semantic richness of Knowledge Graphs (KGs) and the representational power of Graph Embeddings (GEs) to achieve decentralized intelligence. Our architecture empowers individual nodes to locally construct semantic representations of their operational context, iteratively aggregating embeddings through neighbor-based exchanges using GraphSAGE. This iterative local aggregation process results in a dynamically evolving global semantic abstraction called Knowledge Map, enabling coordinated decision-making without centralized control. To validate our approach, we conduct extensive experiments under a distributed resource orchestration use case. We simulate different network topologies and node workloads, analyzing the local semantic drift of individual nodes. Experimental results confirm that our distributed knowledge-sharing mechanism effectively maintains semantic coherence and adaptability, making it suitable for complex and dynamic environments such as Edge Computing, IoT, and multi-agent systems.

Knowledge Graphs-Driven Intelligence for Distributed Decision Systems

TL;DR

The paper tackles the challenge of decentralized coordination in data-heterogeneous, dynamic distributed systems. It introduces Knowledge Sharing, a paradigm that combines Knowledge Graphs with Graph Embeddings (via GraphSAGE) to produce a Knowledge Map as a global semantic abstraction, without centralized control, across a 4-layer architecture (Physical, Storage, Knowledge, Decision). The authors provide formal KG/GE definitions and a detailed workflow for local/global embedding propagation, culminating in a dynamic Knowledge Map that guides autonomous decisions. Preliminary experiments on distributed service orchestration across varied topologies demonstrate the approach's ability to maintain semantic coherence and adaptability in edge, IoT, and multi-agent environments.

Abstract

Modern distributed decision-making systems face significant challenges arising from data heterogeneity, dynamic environments, and the need for decentralized coordination. This paper introduces the Knowledge Sharing paradigm as an innovative approach that uses the semantic richness of Knowledge Graphs (KGs) and the representational power of Graph Embeddings (GEs) to achieve decentralized intelligence. Our architecture empowers individual nodes to locally construct semantic representations of their operational context, iteratively aggregating embeddings through neighbor-based exchanges using GraphSAGE. This iterative local aggregation process results in a dynamically evolving global semantic abstraction called Knowledge Map, enabling coordinated decision-making without centralized control. To validate our approach, we conduct extensive experiments under a distributed resource orchestration use case. We simulate different network topologies and node workloads, analyzing the local semantic drift of individual nodes. Experimental results confirm that our distributed knowledge-sharing mechanism effectively maintains semantic coherence and adaptability, making it suitable for complex and dynamic environments such as Edge Computing, IoT, and multi-agent systems.
Paper Structure (17 sections, 4 equations, 10 figures)

This paper contains 17 sections, 4 equations, 10 figures.

Table of Contents

  1. Introduction
  2. Definitions
  3. Related Work
  4. System Architecture
  5. In-depth Full Architecture Workflow
  6. Knowledge Sharing
  7. Knowledge Embedding and Feature Aggregation
  8. Local Sharing
  9. Global Sharing
  10. Knowledge Map Construction
  11. The Knowledge Cycle
  12. Use Case
  13. Experiments
  14. Experimental Setup
  15. Experiment: Semantic Drift of a Target Node as Local Knowledge Validation
  16. ...and 2 more sections

Figures (10)

  • Figure 1: High-level overview of System Architecture
  • Figure 2: Full Architecture Workflow
  • Figure 3: Distributed Knowledge Sharing between nodes A and B. Each node aggregates its feature vector with its neighbor’s information.
  • Figure 4: Local knowledge exchange between overlapping node neighborhoods enables information propagation at global level.
  • Figure 5: Knowledge Cycle.
  • ...and 5 more figures

Theorems & Definitions (5)

  • definition 1: Knowledge Graph
  • definition 2: KG atomic unit
  • definition 3: Graph Embedding
  • definition 4: GraphSAGE on Knowledge Graphs
  • definition 5: Knowledge Map