Knowledge Graph Embeddings: TransE vs RotatE Link Prediction

Query

Candidate margin ε 2.00

Prediction

Paris —capital_of→ ?

Score(true tail)

–

Rank of true tail

–

Within margin ε

Model

TransE

Top candidates

How it works

A knowledge-graph embedding model places every entity at a point in vector space and represents each relation as an operator, then scores whether a triple (head, relation, tail) is true by how close the operator maps head to tail.

TransE:  score(h,r,t) = ‖ h + r − t ‖
         relation r is one translation vector, shared by every
         triple of that type — "walk from head, land near tail".

RotatE:  score(h,r,t) = ‖ Rot(h, θr) − t ‖
         relation r is a rotation by angle θr about one axis —
         it can only turn h, never stretch or shrink it.

This toy graph has 3 continents, 6 countries and 6 capital cities, each pre-embedded in 3D. part_of triples (country→continent) and capital_of triples (city→country) both move outward to a larger-magnitude point — exactly the kind of hierarchical relation translation handles well and pure rotation cannot, because rotation preserves the head's distance from the origin. Watch the rank and score jump when you switch models on the same query: that gap is the real reason production systems pick a relation family (TransE, RotatE, ComplEx, DistMult…) to match the relation patterns in their data.

◀ Head / Head ▶ — cycle the query's head entity.
Relation — toggle between capital_of and part_of.
TransE / RotatE — switch the scoring model; the ghost marker and arrow show where each model predicts the tail.
Margin ε — any entity scoring under this distance from the prediction is highlighted as a plausible candidate.

Continent Country City True tail

⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.