Beyond Transduction: A Survey on Inductive, Few Shot, and Zero Shot Link Prediction in Knowledge Graphs
Not on the map. Why?
Abstract (arXiv)
Knowledge graphs (KGs) comprise entities interconnected by relations of different semantic meanings. KGs are being used in a wide range of applications. However, they inherently suffer from incompleteness, i.e. entities or facts about entities are missing. Consequently, a larger body of works focuses on the completion of missing information in KGs, which is commonly referred to as link prediction (LP). This task has traditionally and extensively been studied in the transductive setting, where all entities and relations in the testing set are observed during training. Recently, several works have tackled the LP task under more challenging settings, where entities and relations in the test set may be unobserved during training, or appear in only a few facts. These works are known as inductive, few-shot, and zero-shot link prediction. In this work, we conduct a systematic review of existing works in this area. A thorough analysis leads us to point out the undesirable existence of diverging terminologies and task definitions for the aforementioned settings, which further limits the possibility of comparison between recent works. We consequently aim at dissecting each setting thoroughly, attempting to reveal its intrinsic characteristics. A unifying nomenclature is ultimately proposed to refer to each of them in a simple and consistent manner.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 55 of its 134 references that are in the map. First posted on arXiv 8 Dec 2023.
Builds on
55 of 134 references.
References · 55
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
- 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
- 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
- 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
- 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
- 2019Inductive Relation Prediction by Subgraph Reasoningcited by 239
- 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 175
- 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
- 2021Knowledge Graph Reasoning with Relational Digraphcited by 92
- 2020Knowledge Graph Embedding for Link Prediction: A Comparative Analysiscited by 85
38 more
- 2018One-Shot Relational Learning for Knowledge Graphscited by 78
- 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
- 2017Open-World Knowledge Graph Completioncited by 64
- 2019Few-Shot Knowledge Graph Completioncited by 63
- 2020Inductive Entity Representations from Text via Link Predictioncited by 62
- 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
- 2020Relational Message Passing for Knowledge Graph Completioncited by 61
- 2020Communicative Message Passing for Inductive Relation Reasoningcited by 54
- 2018Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embeddingcited by 53
- 2023InGram: Inductive Knowledge Graph Embedding via Relation Graphscited by 52
- 2021Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphscited by 48
- 2020Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Predictioncited by 47
- 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
- 2020Adaptive Attentional Network for Few-Shot Knowledge Graph Completioncited by 42
- 2021Knowledge-aware Zero-Shot Learning: Survey and Perspectivecited by 41
- 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
- 2019Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relationscited by 30
- 2020Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphscited by 30
- 2022Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphscited by 27
- 2022An Open Challenge for Inductive Link Prediction on Knowledge Graphscited by 26
- 2022Inductive Logical Query Answering in Knowledge Graphscited by 26
- 2021Cycle Representation Learning for Inductive Relation Predictioncited by 23
- 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
- 2020Few-shot link prediction via graph neural networks for Covid-19 drug-repurposingcited by 22
- 2020MLMLM: Link Prediction with Mean Likelihood Masked Language Modelcited by 22
- 2021Improving Inductive Link Prediction Using Hyper-Relational Factscited by 22
- 2019Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completioncited by 19
- 2019An Open-World Extension to Knowledge Graph Completion Modelscited by 16
- 2022Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Settingcited by 15
- 2023Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphscited by 14
- 2022RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphscited by 12
- 2022A Hierarchical N-Gram Framework for Zero-Shot Link Predictioncited by 9
- 2021Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphscited by 8
- 2020Inductively Representing Out-of-Knowledge-Graph Entities by Optimal Estimation Under Translational Assumptionscited by 7
- 2022Disconnected Emerging Knowledge Graph Oriented Inductive Link Predictioncited by 7
- 2020Generalized Relation Learning with Semantic Correlation Awareness for Link Predictioncited by 6
- 2022Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Predictioncited by 6
- 2022Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entitiescited by 6
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2025: 2.
2 papers.