AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Towards Unified Neurosymbolic Reasoning on Knowledge Graphs

Qika Lin, Fangzhi Xu, Hao Lu, Kai He, Rui Mao, Jun Liu, Erik Cambria, Mengling Feng

TPAMI 2026 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning · 2 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
combine propositional and FOL reasoning (learned lambda) instead of either alone (ablation)Tunsr · WN18RR, ICEWS14, ICEWS18 (transductive, interpolation, extrapolation)performance curvesImproved
add FOL rule reasoning to propositional reasoning (ablation)Tunsr · transductive and interpolation (WN18RR, ICEWS14)performance curvesMixed
use propositional reasoning instead of FOL reasoning (ablation)Tunsr · extrapolation ICEWS14performance curvesHurt
raise rule length (reasoning iterations) from 2 to 6 (ablation)Tunsr · WN18RR and FB15k-237 V3accuracyImproved
raise rule length beyond 6 (ablation)Tunsr · WN18RR and FB15k-237 V3accuracyNo clear effect
use small node-sampling M and edge-selection N (ablation)Tunsr · ICEWS14 and ICEWS18 extrapolationHits@10Hurt
increase node sampling M beyond 120 (ablation)Tunsr · ICEWS14 and ICEWS18 extrapolationHits@10No clear effect
compare Tunsr against RED-GNNTunsr · WN18RR transductiveHits@10: 62.40 -> 65.78Improved
compare Tunsr against TECHS in extrapolationTunsr · ICEWS14/ICEWS0515/ICEWS18 extrapolationHits@10: 1.37%, 0.96%, and 1.26% gainsImproved
compare Tunsr against TeAST on Hits@1Tunsr · ICEWS0515 interpolationHits@1: 60.40 -> 59.89Hurt
compare Tunsr against ConGLR in 50-negative rankingTunsr · WN18RR V4 (50 negatives)Hits@10: 92.90 -> 89.27Hurt

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