AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Bilinear Scoring Function Search for Knowledge Graph Learning

Yongqi Zhang, Quanming Yao, James Tin-Yau Kwok

TPAMI 2022 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 32 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
use evolutionary search instead of progressive greedy searchAutoBLM+ vs AutoBLM · FB15kMRR: 0.853 -> 0.861Improved
use evolutionary search instead of progressive greedy searchAutoBLM+ vs AutoBLM · ogbl-wikikg2MRR: 0.532 -> 0.546Improved
apply a BLM searched on another dataset (FB15k237 to WN18RR) (ablation)AutoBLM · WN18RRMRR: 0.490 -> 0.462Hurt
apply a BLM searched on another dataset (WN18RR to FB15k237) (ablation)AutoBLM · FB15k237MRR: 0.360 -> 0.345Hurt
add the performance predictor (ablation)AutoBLM/AutoBLM+ · search on KG completion (validation top-8 MRR)mean validation MRR vs timeImproved
use SRF features instead of one-hot features for predictor (ablation)AutoBLM/AutoBLM+ · search on KG completion (validation top-8 MRR)mean validation MRR vs timeImproved
add the filter that removes degenerate structures (ablation)AutoBLM/AutoBLM+ · search on KG completion (validation top-8 MRR)mean validation MRR vs timeImproved
increase initial nonzero count b0 from 1 to 4 without filter (ablation)AutoBLM/AutoBLM+ · search on KG completion (validation top-8 MRR)mean validation MRR vs timeImproved
use progressive/evolutionary search instead of Random, Bayes or Reinforce (ablation)AutoBLM/AutoBLM+ · search on KG completion (validation top-8 MRR)mean validation MRR vs timeImproved
increase K from 3 to 5 (ablation)AutoBLM+ · search on KG completion (validation top-8 MRR)best validation MRRNo clear effect
increase K from 3 to 5 (ablation)AutoBLM+ · WN18RRpredictor running time (min): 1 -> 276Hurt
use parameter sharing (one-shot) to estimate structure quality (ablation)AutoBLM+ · WN18RRSpearman correlation with stand-alone MRR: -0.2686Hurt

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