Machine Learning with Graphs: lecture notes, part 4/4

Some time ago, I finished the Stanford course CS224W Machine Learning with Graphs. This is the last Part 4 of blog posts series where I share my notes from watching lectures. The rest you can find here: 1, 2, 3.

Lecture 17 — Reasoning over Knowledge Graphs

Slides, Video

Knowledge graphs are graphs that capture entities, types, and relationships. Nodes in these graphs are entities that are labeled with their types and edges between two nodes capture relationships between entities.

Examples are bibliographical network (node types are paper, title, author, conference, year; relation types are pubWhere, pubYear, hasTitle, hasAuthor, cite), social network (node types are account, song, post, food, channel; relation types are friend, like, cook, watch, listen).

Knowledge graphs in practice:

• Google Knowledge Graph.
• Amazon Product Graph.
• Facebook Graph API.
• IBM Watson.
• Microsoft Satori.
• Project Hanover/Literome.
• LinkedIn Knowledge Graph.
• Yandex Object Answer.