Papers › Zero-Shot Learning with Common Sense Knowledge Graphs
Zero-Shot Learning with Common Sense Knowledge Graphs
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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