AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs

Pengda Qin, Xin Wang, Wenhu Chen, Chunyun Zhang, Weiran Xu, William Yang Wang

AAAI 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 75 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 ZSGAN_KG with DistMult rather than ZS-DistMultNELL-ZS zero-shot link prediction · NELL-ZSMRR: 0.235 -> 0.253Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultNELL-ZS zero-shot link prediction · NELL-ZSHits@10: 32.6 -> 37.1Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultNELL-ZS zero-shot link prediction · NELL-ZSHits@5: 28.4 -> 30.5Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultNELL-ZS zero-shot link prediction · NELL-ZSHits@1: 18.5 -> 19.4Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultWiki-ZS zero-shot link prediction · Wiki-ZSMRR: 0.189 -> 0.208Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultWiki-ZS zero-shot link prediction · Wiki-ZSHits@10: 23.6 -> 29.4Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultWiki-ZS zero-shot link prediction · Wiki-ZSHits@5: 21.0 -> 24.1Improved
Use ZSGAN_KG with DistMult rather than ZS-DistMultWiki-ZS zero-shot link prediction · Wiki-ZSHits@1: 16.1 -> 16.5Improved
Use Word2Vec rather than BERT word representations (ablation)ZSGAN_KG with DistMult · NELL-ZSMRR: 0.237 -> 0.253Improved
Use Word2Vec rather than BERT word representations (ablation)ZSGAN_KG with DistMult · Wiki-ZSMRR: 0.175 -> 0.208Improved
Replace the bag-of-words text input with a CNN or LSTM text encoder (ablation)ZSGAN_KG · Zero-shot relational learninglink prediction performanceHurt

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