atlas

Research map / Graph learning / Knowledge and temporal graphs

Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs

NeurIPS 2020 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning · 94 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Beta distribution embeddings (BetaE) vs boxes (q2b)KG query embedding · FB15k EPFOMRR: 38.0 -> 41.6Helped
BetaE vs q2bKG query embedding · FB15k-237 EPFOMRR: 20.1 -> 20.9Helped
BetaE vs q2bKG query embedding · NELL995 EPFOMRR: 22.9 -> 24.6Helped
BetaE vs q2bKG query embedding · FB15k 1pMRR: 68.0 -> 65.1Hurt
BetaE vs q2bKG query embedding · NELL995 2pMRR: 14.0 -> 13.0Hurt
model disjunction via De Morgan instead of DNF (ablation)BetaE · FB15k 2uMRR: 40.1 -> 25.0Hurt
model disjunction via De Morgan instead of DNF (ablation)BetaE · NELL995 upMRR: 8.5 -> 8.6No clear effect
Beta differential entropy vs box size as uncertaintyquery embedding · FB15k-237 2pSpearman correlation: 0.226 -> 0.503Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy