What are multi-hop relational paths in the context of knowledge graphs (KGs)?
I tried looking it up online, but didn't find a simple explanation.
Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.Sign up to join this community
Before trying to explain this term in your context, let me briefly describe the term in other contexts.
In computer networking, the term "hop" refers to a node (e.g. a router) that a packet goes through before reaching its destination from its source. In a multi-hop situation, you have several nodes involved in the process of sending the packet from the source to the destination.
A knowledge graph is a graph that accumulates and conveys knowledge of the real world, where nodes represent entities of interest and edges relations between those entities.
So, multi-hop relational paths are probably relational paths involving more than one node or edge in the knowledge graph.
But what do we mean by "relational"?
If you are familiar with the basics of databases, the word "relational" shouldn't be so unfamiliar. In fact, there the so-called relational databases, relational models and relational algebra. Intuitively, the word "relational" is used to denote what you think it denotes, i.e. relations. See also What a relational database is by Oracle.
And what is a path?
In section 2.2.3 of the tutorial Knowledge Graphs, Aidan Hogan et al. provide a description of a path (expressions) in the context of knowledge graphs
Navigational graph patterns. A key feature that distinguishes graph query languages is the ability to include path expressions in queries. A path expression $r$ is a regular expression that allows matching arbitrary-length paths between two nodes, which is expressed as a regular path query $(x,r,y)$, where $x$ and $y$ can be variables or constants (or even the same term).