This repository provides comprehensive lecture materials for a graduate-level course on Knowledge Graphs, covering foundational concepts, advanced techniques, and recent research trends. It is designed for graduate students, researchers, and engineers interested in building and applying knowledge graph technologies. The course materials offer a structured learning path from basic knowledge representation to cutting-edge applications with Large Language Models.

How It Works

The course systematically covers key knowledge graph lifecycle stages: introduction, representation, modeling, extraction (entity, relation, event), fusion, and applications with LLMs. It delves into various techniques, including traditional knowledge representation methods, machine learning-based extraction, deep learning approaches, and recent advancements in KG-LLM integration. The curriculum emphasizes both theoretical underpinnings and practical considerations, referencing seminal and recent research papers.

Quick Start & Requirements

• Access: Download lecture slides (PDFs) and supplementary papers.
• Prerequisites: Familiarity with machine learning, natural language processing, and graph theory is recommended. No specific software installation is required to access the course materials.
• Resources: Links to course materials for 2023, 2024, and 2025 are provided, along with extensive lists of relevant academic papers.

Highlighted Details

• Covers the integration of Knowledge Graphs with Large Language Models (LLMs), including KG for LLM and LLM for KG applications.
• Detailed breakdown of knowledge extraction techniques: entity recognition, relation extraction, and event extraction, with a focus on deep learning methods.
• Extensive bibliography of foundational and recent research papers in knowledge graph construction, representation, extraction, fusion, reasoning, and storage.
• Includes a section on "Latest Progress Papers" from 2018-2020, offering insights into the field's evolution.

Maintenance & Community

• The course is associated with Professor Peng Wang from Southeast University.
• Contact information (email) is provided for questions, discussions, and suggestions.
• The repository structure suggests regular updates, with materials provided for multiple academic years (2023, 2024, 2025).

Licensing & Compatibility

• The repository itself does not specify a license. The content consists of lecture materials and links to academic papers, which are subject to their respective copyrights and licenses.

Limitations & Caveats

• This repository primarily contains lecture slides and paper references, not executable code or datasets for hands-on practice.
• The focus is academic, with an emphasis on research papers rather than specific software tools or frameworks.