Graphs to Graph Neural Networks: From Fundamentals to Applications — Part 2a: Knowledge Graphs

Isaac Kargar
15 min readApr 16
Source

Isaac: In this post, I will start to learn about knowledge graphs. I also started to use the more powerful model of ChatGPT with the GPT-4 model. I hope the responses are better now. I start by asking ChatGPT to give me some questions to learn about knowledge graphs:

I want to learn about knowledge graphs after learning about graphs. Give me 30 questions that I can use to interact with you and learn about this topic. Consider also learning about deep learning on knowledge graphs.

Let’s dive into the responses and explore them.

1. What is a knowledge graph?

A knowledge graph is a structured representation of knowledge that consists of entities, relationships, and their attributes. It is typically visualized as a graph, where nodes represent entities (e.g., people, places, concepts) and edges represent relationships between these entities. The relationships can be labeled with properties or attributes to provide more context and information.

Knowledge graphs are used to store and organize information in a way that makes it easily accessible and understandable by both humans and machines. They can be employed in various applications such as semantic search, recommendation systems, natural language processing, and artificial intelligence to improve the quality and relevance of results, facilitate information retrieval, and enable reasoning and inference based on the available knowledge.

2. What are the main components of a knowledge graph?

The main components of a knowledge graph are:

  1. Entities: Entities are the fundamental building blocks of a knowledge graph. They represent real-world objects, concepts, or abstract ideas such as people, places, organizations, events, or even intangible concepts like emotions or ideas. Entities are typically represented as nodes in the graph.
  2. Relationships: Relationships, also known as edges or links, connect entities in the knowledge graph. They represent the associations, connections, or interactions between the entities, providing context and structure to the information. Relationships can be of various types, such as “is a,” “has,”…
Isaac Kargar

Co-Founder and CIO @ SUPPLYZ: https://www.supplyz.eu | Ph.D. candidate at the Intelligent Robotics Group at Aalto University | https://kargarisaac.github.io/