Papers › Zero-Shot Learning with Common Sense Knowledge Graphs

Zero-Shot Learning with Common Sense Knowledge Graphs

18 Jun 2020arXiv:2006.10713archive 2025-07-28

Nihal V. Nayak, Stephen H. Bach

Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples. We propose to learn class representations by embedding nodes from common sense knowledge graphs in a vector space. Common sense knowledge graphs are an untapped source of explicit high-level knowledge that requires little human effort to apply to a range of tasks. To capture the knowledge in the graph, we introduce ZSL-KG, a general-purpose framework with a novel transformer graph convolutional network (TrGCN) for generating class representations. Our proposed TrGCN architecture computes non-linear combinations of node neighbourhoods. Our results show that ZSL-KG improves over existing WordNet-based methods on five out of six zero-shot benchmark datasets in language and vision.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

BatsResearch/nayak-arxiv20-code officialmentioned in papermentioned on GitHubpytorch report
BatsResearch/zsl-kg officialmentioned in papermentioned on GitHubpytorch report
batsresearch/nayak-tmlr22-code officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Generalized Zero-Shot LearningKnowledge GraphsZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Zero-Shot Learning AwA2 ZSL-KG Harmonic mean 74.58 #2 of 4 Archive leaderboard report
Generalized Zero-Shot Learning BBN Pronoun Coreference and Entity Type Corpus ZSL-KG F1 26.69 #1 of 1 Archive leaderboard report
Generalized Zero-Shot Learning OntoNotes ZSL-KG F1 45.21 #1 of 1 Archive leaderboard report
Generalized Zero-Shot Learning aPY - 0-Shot ZSL-KG Harmonic mean 61.57 #1 of 1 Archive leaderboard report
Zero-Shot Learning AwA2 ZSL-KG average top-1 classification accuracy 78.08 #2 of 4 Archive leaderboard report
Zero-Shot Learning SNIPS ZSL-KG Accuracy 88.98 #1 of 1 Archive leaderboard report
Zero-Shot Learning aPY - 0-Shot ZSL-KG Top-1 60.54 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections