AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

Jinheon Baek, Dong Bok Lee, Sung Ju Hwang

NeurIPS 2020 · Graph learning › Knowledge and temporal graphs · approach: Temporal knowledge graph reasoning · 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
Add transductive message passing between unseen entitiesI-GEN, yielding T-GEN · FB15k-237 and NELL-995 OOG link predictionMRR: .348 -> .367 (FB15k-237 1-shot); .367 -> .382 (FB15k-237 3-shot); .278 -> .282 (NELL-995 1-shot); .285 -> .291 (NELL-995Improved
Add transductive message passing between unseen entitiesI-GEN, yielding T-GEN · DeepDDI and BIOSNAP-sub 3-shot OOGROC: .946 -> .954 (DeepDDI); .608 -> .625 (BIOSNAP-sub)Improved
Add transductive message passing between unseen entitiesI-GEN, yielding T-GEN · DeepDDI and BIOSNAP-sub 3-shot OOGPR: .681 -> .708 (DeepDDI); .062 -> .067 (BIOSNAP-sub)Improved
Add transductive message passing between unseen entitiesI-GEN, yielding T-GEN · DeepDDI and BIOSNAP-sub 3-shot OOGAcc: .807 -> .815 (DeepDDI); .073 -> .089 (BIOSNAP-sub)Improved
Add stochastic inference to the transductive layerDeterministic T-GEN · Unseen-to-unseen link predictionMRRImproved
Remove many-shot-to-few-shot transfer strategy (ablation)I-GEN · FB15k-237 and NELL-995 1- and 3-shot OOGMRR: .348 -> .344 and .367 -> .362 (FB15k-237); .278 -> .272 and .285 -> .277 (NELL-995)Hurt
Remove many-shot-to-few-shot transfer strategy (ablation)T-GEN · FB15k-237 and NELL-995 1- and 3-shot OOGMRR: .367 -> .362 and .382 -> .381 (FB15k-237); .282 -> .273 and .291 -> .290 (NELL-995)Hurt
Use random rather than pre-trained DistMult embeddings (ablation)I-GEN · FB15k-237 1- and 3-shot OOGMRR: .348 -> .309; .367 -> .319Hurt
Use random rather than pre-trained DistMult embeddings (ablation)T-GEN · FB15k-237 1- and 3-shot OOGMRR: .367 -> .349; .382 -> .360Hurt
Replace DistMult initialization and score function with TransE (ablation)I-GEN and T-GEN · FB15k-237 OOG link predictionMRRNo clear effect
Train on 1-shot cases and test on 3-shot cases (ablation)GEN · FB15k-237 and NELL-995 OOG link predictionMRRImproved

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