Knowledge Tree
graph traversal
Also known as: graph traversal algorithms
Facts (12)
Sources
Construction of intelligent decision support systems through ... - Nature nature.com Oct 10, 2025 3 facts
referenceThe KG-Only baseline utilizes conventional knowledge graph reasoning algorithms, such as graph traversal, logical inference, and constraint satisfaction, to produce entity recommendations without generative components.
referenceThe retrieval optimization module incorporates knowledge graph structure into a multi-faceted strategy that combines semantic search (using dense vector embeddings), structure-aware graph traversal (guided exploration of topology), and logical inference (using domain rules for implicit conclusions).
procedureThe retrieval optimization module in the Integrated Knowledge-Enhanced Decision Support framework integrates three approaches: (1) dense vector retrieval using domain-adapted sentence transformers, (2) graph traversal using personalized PageRank to propagate the relevant retriever, and (3) logical inference via integration with automated reasoning engines.
Knowledge Graphs vs RAG: When to Use Each for AI in 2026 - Atlan atlan.com Feb 12, 2026 2 facts
claimPure vector search retrieves semantically similar text without understanding connections, while pure graph traversal misses content not explicitly modeled as relationships; GraphRAG addresses both by providing structured reasoning through relationship paths, broad coverage through semantic similarity, explainable answers with traceable provenance, and flexibility to handle both structured and unstructured knowledge.
claimGraphRAG architectures combine graph traversal with vector search to provide both structured reasoning and broad coverage.
LLM-Powered Knowledge Graphs for Enterprise Intelligence and ... arxiv.org Mar 11, 2025 2 facts
claimThe knowledge-graph-enhanced LLM system facilitates data-driven decision-making by leveraging graph analytics and LLMs to translate natural language queries into graph traversal and analytics operations, allowing for the retrieval and segmentation of relevant statistics.
procedureThe Expertise Discovery process involves users uploading discussion threads or documents, which the system processes to extract and rank skills, perform graph traversal, and refine results using LLM-based re-ranking.
Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org 1 fact
claimRDF has undergone extensive standardization over the last 25 years, whereas Property Graph Models (PGM) have become increasingly popular for advanced database and network applications like graph traversal and network analysis.
Combining Knowledge Graphs With LLMs | Complete Guide - Atlan atlan.com Jan 28, 2026 1 fact
claimModern knowledge graph-LLM systems combine graph traversal with vector similarity to retrieve both directly connected nodes and semantically related concepts, addressing limitations of pure graph or pure vector retrieval.
A survey on augmenting knowledge graphs (KGs) with large ... link.springer.com Nov 4, 2024 1 fact
claimKnowledge Graphs enable real-time data analysis and decision-making by fetching relevant data across relationships using high-speed graph traversal algorithms.
Large Language Models Meet Knowledge Graphs for Question ... arxiv.org Sep 22, 2025 1 fact
claimJoint KG–LLM reasoning remains inefficient because large-scale graph traversal is computationally intensive and time-consuming.
Practices, opportunities and challenges in the fusion of knowledge ... frontiersin.org 1 fact
claimKnowledge graph-enhanced large language models often incur high computational overhead due to the necessity of graph traversal, entity linking, and dynamic retrieval during inference, which introduces latency that hinders deployment in real-time applications like dialogue systems, autonomous agents, and online recommendation.