AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

Xueyuan Lin, Haihong E, Chengjin Xu, Gengxian Zhou, Haoran Luo, Tianyi Hu, Fenglong Su, Ningyuan Li, Mingzhi Sun

NeurIPS 2023 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning · 5 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
replace fuzzy entity part with ConE geometric entity part (X(ConE)) (ablation)TFLEX · ICEWS14avg_e MRR: 56.79 -> 40.93Hurt
remove the time part (FLEX) (ablation)TFLEX · ICEWS14avg_e MRR: 56.79 -> 43.67Hurt
remove the time part (FLEX) (ablation)TFLEX · GDELT-500avg_e MRR: 19.60 -> 19.07Hurt
merge entity and timestamp features into one feature (X-1F) (ablation)TFLEX · ICEWS05-15avg_e MRR: 48.99 -> 49.90Improved
merge entity and timestamp features into one feature (X-1F) (ablation)TFLEX · GDELT-500avg_e MRR: 19.60 -> 17.92Hurt
merge entity and timestamp features into one feature (X-1F) (ablation)TFLEX · ICEWS14avg_e MRR: 56.79 -> 56.89No clear effect
remove entity and time logic (X-logic) (ablation)TFLEX · ICEWS05-15avg_e MRR: 48.99 -> 44.80Hurt
remove entity and time logic (X-logic) (ablation)TFLEX · GDELT-500avg_e MRR: 19.60 -> 17.36Hurt
remove entity and time logic (X-logic) (ablation)TFLEX · ICEWS14avg_e MRR: 56.79 -> 56.64No clear effect
train on temporal complex queries instead of only one-hop queries (TFLEX vs TFLEX-1p) (ablation)TFLEX · TKGC (ICEWS14, ICEWS05-15, GDELT)MRR: 43.9 -> 48.2Improved
use TFLEX instead of ConE baseline for query answeringConE · ICEWS14avg_e MRR: 41.94 -> 56.79Improved
embedding dimension d and margin gamma sweepTFLEX · ICEWS14, ICEWS05-15, GDELT-500MRRMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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