Knowledge Graphs
WN18RR
Structure
1Graphs
40,943Nodes
93,003Edges
11Classes
Coverage
223Results
1Variants
28Papers
- A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
- On the Safety of Graph Representation Learning On the Safety of Graph Representation Learning
- KDD 2026: Generalizing GNNs with Tokenized Mixture of Experts Generalizing GNNs with Tokenized Mixture of Experts KDD 2026
- Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach
- FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
- KDD 2025: Quantizing Text-attributed Graphs for Semantic-Structural Integration Quantizing Text-attributed Graphs for Semantic-Structural Integration KDD 2025
- NeurIPS 2025: Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement NeurIPS 2025
- Relation-Aware Graph Foundation Model Relation-Aware Graph Foundation Model
- ICML 2024: Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees ICML 2024
- NeurIPS 2024: GFT: Graph Foundation Model with Transferable Tree Vocabulary GFT: Graph Foundation Model with Transferable Tree Vocabulary NeurIPS 2024
- NeurIPS 2024: Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs NeurIPS 2024
- NeurIPS 2024: A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning NeurIPS 2024
- ICML 2024: KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning ICML 2024
- KDD 2024: UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs KDD 2024
- ICLR 2023: Towards Foundation Models for Knowledge Graph Reasoning Towards Foundation Models for Knowledge Graph Reasoning ICLR 2023
- ICLR 2023: One for All: Towards Training One Graph Model for All Classification Tasks One for All: Towards Training One Graph Model for All Classification Tasks ICLR 2023
- WWW 2023: Knowledge Graph Completion with Counterfactual Augmentation Knowledge Graph Completion with Counterfactual Augmentation WWW 2023
- NeurIPS 2023: A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs NeurIPS 2023
- A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal
- Knowledge Graph Contrastive Learning based on Relation-Symmetrical Structure Knowledge Graph Contrastive Learning based on Relation-Symmetrical Structure
- NeurIPS 2022: A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs NeurIPS 2022
- NeurIPS 2021: AutoGEL: An Automated Graph Neural Network with Explicit Link Information AutoGEL: An Automated Graph Neural Network with Explicit Link Information NeurIPS 2021
- WWW 2021: Knowledge Graph Reasoning with Relational Digraph Knowledge Graph Reasoning with Relational Digraph WWW 2021
- NeurIPS 2021: Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction NeurIPS 2021
- IJCAI 2020: Multi-hop Attention Graph Neural Networks Multi-hop Attention Graph Neural Networks IJCAI 2020
- ICLR 2019: Composition-based Multi-Relational Graph Convolutional Networks Composition-based Multi-Relational Graph Convolutional Networks ICLR 2019
- ICLR 2018: RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space ICLR 2018
- AAAI 2017: Knowledge Graphs Knowledge Graphs AAAI 2017
11-relation knowledge-graph completion Knowledge graph link prediction on WordNet (40,943 entities, 11 relations). Inputs are directed subject-relation-object triples with learned embeddings. Filtered ranking is required; WN18 has inverse-relation leakage. Evaluated by MRR.
Dataset details
Task
Knowledge graph link prediction on WordNet (40,943 entities, 11 relations). The primary catalog metric is MRR.
Data
Knowledge graph link prediction on WordNet (40,943 entities, 11 relations). The cataloged artifact reports 1 graphs, 11 target classes or tasks.
Features
The raw input is a set of directed subject-relation-object triples. Entity and relation embeddings are learned inputs; reciprocal edges, inverse relations, and filtered candidate sets are evaluation or preprocessing choices.
Splits and evaluation
The catalog records these protocols or variants: Standard split. Evaluation uses MRR (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
Filtered ranking removes other known true triples but the graph is incomplete, so sampled corruptions can be false negatives. WN18 and FB15k contain inverse-relation leakage; use WN18RR or FB15k-237 when evaluating relational generalization.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | MRR ↑ | ACC | Accuracy | F1 | Hits@10 | MRR (Link Classification header) | MRR (Link Classification header; source does not print 'MRR' literally) | Paper |
|---|---|---|---|---|---|---|---|---|---|
| 1 | FedSage | 0.8426
±
0.0026 | — | — | — | — | — | — | |
| 2 | FED-PUB | 0.8348
±
0.0025 | — | — | — | — | — | — | |
| 3 | FedAvg | 0.8252
±
0.0023 | — | — | — | — | — | — | |
| 4 | GAT | 0.8244
±
0.0037 | — | — | — | — | — | — | |
| 5 | MOON | 0.8231
±
0.0025 | — | — | — | — | — | — | |
| 6 | Linear | 0.8225
±
0.0023 | — | — | — | — | — | — | |
| 7 | GCN | 0.8171
±
0.0030 | — | — | — | — | — | — | |
| 8 | GraphSAGE | 0.8152
±
0.0024 | — | — | — | — | — | — | |
| 9 | GAT | 0.8135
±
0.0031 | — | — | — | — | — | — | |
| 10 | FedSage | 0.8126
±
0.0026 | — | — | — | — | — | — | |
| 11 | GIN | 0.8124
±
0.0055 | — | — | — | — | — | — | |
| 12 | FED-PUB | 0.8065
±
0.0030 | — | — | — | — | — | — | |
| 13 | MOON | 0.8062
±
0.0042 | — | — | — | — | — | — | |
| 14 | GraphSAGE | 0.8033
±
0.0006 | — | — | — | — | — | — | |
| 15 | GAT | 0.8016 | — | — | — | — | — | — | |
| 16 | FedAvg | 0.8007
±
0.0012 | — | — | — | — | — | — | |
| 17 | OFA | 0.8000 | — | — | — | — | — | — | |
| 18 | GIN | 0.7994
±
0.0039 | — | — | — | — | — | — | |
| 19 | Linear | 0.7983
±
0.0030 | — | — | — | — | — | — | |
| 20 | GCN | 0.7974
±
0.0014 | — | — | — | — | — | — | |
| 21 | Linear | 0.7850 | — | — | — | — | — | — | |
| 22 | NeuralLP | 0.7440 | — | — | — | — | — | — | |
| 23 | DRUM | 0.7440 | — | — | — | — | — | — | |
| 24 | GCN | 0.7379 | — | — | — | — | — | — | |
| 25 | RED-GNN | 0.7010 | — | — | — | — | — | — | |
| 26 | RuleN | 0.6680 | — | — | — | — | — | — | |
| 27 | DRUM | 0.6660 | — | — | — | — | — | — | |
| 28 | SimKGC | 0.6660 | — | — | — | — | — | — | |
| 29 | SimKGC-SymCL | 0.6570 | — | — | — | — | — | — | |
| 30 | SimKGC | 0.6520 | — | — | — | — | — | — | |
| 31 | Neural LP | 0.6490 | — | — | — | — | — | — | |
| 32 | Supervised SOTA | 0.6400 | — | — | — | — | — | — | |
| 33 | GraIL | 0.6270 | — | — | — | — | — | — | |
| 34 | STAG + Linear Probing | 0.5830 | — | — | — | — | — | — | |
| 35 | KnowFormer | 0.5790 | — | — | — | — | — | — | |
| 36 | SCR-MPNet | 0.5780 | — | — | — | — | — | — | |
| 37 | SCR(3g) | 0.5760 | — | — | — | — | — | — | |
| 38 | SCR-MiniLM | 0.5760 | — | — | — | — | — | — | |
| 39 | SCR-DistilBert | 0.5760 | — | — | — | — | — | — | |
| 40 | SCR-Ontology | 0.5700 | — | — | — | — | — | — | |
| 41 | SCR-One | 0.5690 | — | — | — | — | — | — | |
| 42 | ULTRA(4g) | 0.5670 | — | — | — | — | — | — | |
| 43 | AdaProp | 0.5620 | — | — | — | — | — | — | |
| 44 | KGCF | 0.5530 | — | — | — | — | — | — | |
| 45 | ProLINK(3g) | 0.5530 | — | — | — | — | — | — | |
| 46 | NBFnet | 0.5510 | — | — | — | — | — | — | |
| 47 | Supervised SOTA | 0.5510 | — | — | — | — | — | — | |
| 48 | A*Net | 0.5490 | — | — | — | — | — | — | |
| 49 | KG-ICL finetune | 0.5360 | — | — | — | — | — | — | |
| 50 | C-MPNN-basic | 0.5340 | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time