# Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

arXiv: https://arxiv.org/abs/2006.06648 · HTML: https://mlsanity.com/paper/2006.06648/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2020.

## Built on by (most cited first, 30 of 47)

- [Handling Distribution Shifts on Graphs: An Invariance Perspective](https://mlsanity.com/paper/2202.02466/) (2022)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs](https://mlsanity.com/paper/2106.12144/) (2021)
- [Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift](https://mlsanity.com/paper/2211.02843/) (2022)
- [Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding](https://mlsanity.com/paper/2110.14170/) (2021)
- [Relational Message Passing for Fully Inductive Knowledge Graph Completion](https://mlsanity.com/paper/2210.03994/) (2022)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Improving Inductive Link Prediction Using Hyper-Relational Facts](https://mlsanity.com/paper/2107.04894/) (2021)
- [Graph Self-supervised Learning with Accurate Discrepancy Learning](https://mlsanity.com/paper/2202.02989/) (2022)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs](https://mlsanity.com/paper/2302.01859/) (2023)
- [Few-Shot Learning on Graphs](https://mlsanity.com/paper/2203.09308/) (2022)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [On the Evolution of Knowledge Graphs: A Survey and Perspective](https://mlsanity.com/paper/2310.04835/) (2023)
- [Facing Changes: Continual Entity Alignment for Growing Knowledge Graphs](https://mlsanity.com/paper/2207.11436/) (2022)
- [Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information](https://mlsanity.com/paper/2211.08169/) (2022)
- [BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning](https://mlsanity.com/paper/2211.14568/) (2022)
- [Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding](https://mlsanity.com/paper/2302.01849/) (2023)
- [Meta-Learning with Graph Neural Networks: Methods and Applications](https://mlsanity.com/paper/2103.00137/) (2021)
- [Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction](https://mlsanity.com/paper/2209.01397/) (2022)
- [Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training](https://mlsanity.com/paper/2407.14732/) (2024)
- [Survey on English Entity Linking on Wikidata](https://mlsanity.com/paper/2112.01989/) (2021)
- [Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities](https://mlsanity.com/paper/2208.10378/) (2022)
- [A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledge](https://mlsanity.com/paper/2301.01172/) (2023)
- [A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning](https://mlsanity.com/paper/2402.01440/) (2024)
- [Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs](https://mlsanity.com/paper/2504.13429/) (2025)
- [Metric Based Few-Shot Graph Classification](https://mlsanity.com/paper/2206.03695/) (2022)
- [Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach](https://mlsanity.com/paper/2307.01204/) (2023)
- [Zero-Shot Relational Learning for Multimodal Knowledge Graphs](https://mlsanity.com/paper/2404.06220/) (2024)

## Abstract (arXiv)

Many practical graph problems, such as knowledge graph construction and drug-drug interaction prediction, require to handle multi-relational graphs. However, handling real-world multi-relational graphs with Graph Neural Networks (GNNs) is often challenging due to their evolving nature, as new entities (nodes) can emerge over time. Moreover, newly emerged entities often have few links, which makes the learning even more difficult. Motivated by this challenge, we introduce a realistic problem of few-shot out-of-graph link prediction, where we not only predict the links between the seen and unseen nodes as in a conventional out-of-knowledge link prediction task but also between the unseen nodes, with only few edges per node. We tackle this problem with a novel transductive meta-learning framework which we refer to as Graph Extrapolation Networks (GEN). GEN meta-learns both the node embedding network for inductive inference (seen-to-unseen) and the link prediction network for transductive inference (unseen-to-unseen). For transductive link prediction, we further propose a stochastic embedding layer to model uncertainty in the link prediction between unseen entities. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction. The results show that our model significantly outperforms relevant baselines for out-of-graph link prediction tasks.