AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Path Ranking with Attention to Type Hierarchies

Weiyu Liu, Angel Daruna, Zsolt Kira, Sonia Chernova

AAAI 2020 · Graph learning › Knowledge and temporal graphs · approach: Inductive knowledge graph completion · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
Add attention-based type selection over entity type hierarchiesPath-RNN with LogSumExp pooling · WN18RRMAP%: 50.82 -> 74.51; 51.08 -> 74.51; 67.16 -> 74.51Improved
Add attention-based type selection over entity type hierarchiesPath-RNN with LogSumExp pooling · FB15k-237MAP%: 45.64 -> 54.09; 51.23 -> 54.09; 52.17 -> 54.09Improved
Use attention pooling over path representations instead of Max, Average, or LogSumExp pooling (ablation)APR · WN18RRMAP%: 73.23/80.30/74.51 -> 84.91Improved
Use attention pooling over path representations instead of Max, Average, or LogSumExp pooling (ablation)APR · FB15k-237MAP%: 52.40/54.72/54.09 -> 57.35Improved
Learn entity abstraction levels with attention instead of fixing them to the most abstract level (ablation)APR D · WN18RRMAP%: 81.17 -> 84.91Improved
Learn entity abstraction levels with attention instead of fixing them to the most abstract level (ablation)APR D · FB15k-237MAP%: 49.71 -> 57.35Improved
Learn entity abstraction levels with attention instead of fixing them to the most specific level (ablation)APR D · WN18RRMAP%: 82.66 -> 84.91Improved
Learn entity abstraction levels with attention instead of fixing them to the most specific level (ablation)APR D · FB15k-237MAP%: 54.55 -> 57.35Improved
Use relation, type, and entity information with direct feature aggregation rather than learned type abstractionPath-RNN C · WN18RRMAP%: 67.16 -> 51.08Hurt
Use APR with learned type abstraction and LogSumExp pooling instead of the strongest prior path-ranking resultWN18RR · WN18RRMAP%: 67.16 -> 74.51Improved
Use APR with learned type abstraction and LogSumExp pooling instead of the strongest prior path-ranking resultFB15k-237 · FB15k-237MAP%: 52.17 -> 54.09Improved
Use APR D instead of ComplEx-N3Knowledge base fact prediction · WN18RRMAP%: 40.89 -> 84.91Improved

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