AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

Yongqi Zhang, Quanming Yao, Lei Chen

NeurIPS 2020 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 17 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
Search a task-specific recurrent architecture over relational pathsKG entity alignment · DBP-WD Normal, DBP-YG Normal, EN-FR Normal, EN-DE NormalMRR: DBP-WD: 0.49 -> 0.51; DBP-YG: 0.50 -> 0.51; EN-FR: 0.44 -> 0.46; EN-DE: 0.57 -> 0.59Improved
Search a task-specific recurrent architecture over relational pathsKG link prediction · WN18-RR and YAGO3-10MRR: WN18-RR: 0.47 -> 0.48; YAGO3-10: 0.48 -> 0.51Improved
Search a task-specific recurrent architecture over relational pathsKG link prediction · FB15k-237MRR: 0.32 -> 0.32No clear effect
Use longer relational-path modeling with intermediate entities and relations (ablation)Countries S3 · Countries S3AUC-PR: P1 0.933±0.031; P2 0.952±0.023; P3 0.961±0.016; P4 0.964±0.015; Interstellar 0.968± 0.007Improved
Include entities along the path rather than only relations (ablation)Countries relational-path models · Countries S1 and S2AUC-PR: S1: P3 0.992±0.001 -> P4 0.977±0.028; S2: P3 1.000±0.000 -> P4 0.984±0.010Hurt
Use a one-shot parameter-sharing search across the full architecture space (ablation)Interstellar architecture search · Entity alignment and link prediction searchvalidation performanceHurt
Split macro and micro architecture search, evaluating macro candidates stand-alone and micro candidates with parameter sharingInterstellar architecture search · Entity alignment and link prediction searchsearch efficiency and reliabilityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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