# Few-shot Relational Reasoning via Connection Subgraph Pretraining

arXiv: https://arxiv.org/abs/2210.06722 · HTML: https://mlsanity.com/paper/2210.06722/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [Boosting Few-Shot Visual Learning with Self-Supervision](https://mlsanity.com/paper/1906.05186/) (2019)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [One-Shot Relational Learning for Knowledge Graphs](https://mlsanity.com/paper/1808.09040/) (2018)
- [Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/1909.01515/) (2019)
- [Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/1911.11298/) (2019)
- [Relational Message Passing for Knowledge Graph Completion](https://mlsanity.com/paper/2002.06757/) (2020)
- [Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier](https://mlsanity.com/paper/2101.00562/) (2021)
- [Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations](https://mlsanity.com/paper/1908.11513/) (2019)

## Built on by (most cited first, 18 of 18)

- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Towards Foundation Models for Knowledge Graph Reasoning](https://mlsanity.com/paper/2310.04562/) (2023)
- [Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases](https://mlsanity.com/paper/2303.14617/) (2023)
- [A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes](https://mlsanity.com/paper/2307.06046/) (2023)
- [Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Types](https://mlsanity.com/paper/2302.01313/) (2023)
- [Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2304.08183/) (2023)
- [Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs](https://mlsanity.com/paper/2302.01859/) (2023)
- [GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning](https://mlsanity.com/paper/2511.05592/) (2025)
- [EFOk-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation](https://mlsanity.com/paper/2307.13701/) (2023)
- [SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning](https://mlsanity.com/paper/2304.10297/) (2023)
- [Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach](https://mlsanity.com/paper/2307.01204/) (2023)
- [RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.15124/) (2026)
- [Retrieving Minimal and Sufficient Reasoning Subgraphs with Graph Foundation Models for Path-aware GraphRAG](https://mlsanity.com/paper/2603.07179/) (2026)
- [NeuralKG-ind: A Python Library for Inductive Knowledge Graph Representation Learning](https://mlsanity.com/paper/2304.14678/) (2023)
- [MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning](https://mlsanity.com/paper/2510.23013/) (2025)
- [Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods](https://mlsanity.com/paper/2510.16609/) (2025)
- [Chimaera: A Mixture-of-Graph-Experts Architecture for Cross-Task and Cross-Dataset Graph Learning](https://mlsanity.com/paper/2609.08709/) (2026)

## Abstract (arXiv)

Few-shot knowledge graph (KG) completion task aims to perform inductive reasoning over the KG: given only a few support triplets of a new relation bowtie (e.g., (chop,bowtie,kitchen), (read,bowtie,library), the goal is to predict the query triplets of the same unseen relation bowtie, e.g., (sleep,bowtie,?). Current approaches cast the problem in a meta-learning framework, where the model needs to be first jointly trained over many training few-shot tasks, each being defined by its own relation, so that learning/prediction on the target few-shot task can be effective. However, in real-world KGs, curating many training tasks is a challenging ad hoc process. Here we propose Connection Subgraph Reasoner (CSR), which can make predictions for the target few-shot task directly without the need for pre-training on the human curated set of training tasks. The key to CSR is that we explicitly model a shared connection subgraph between support and query triplets, as inspired by the principle of eliminative induction. To adapt to specific KG, we design a corresponding self-supervised pretraining scheme with the objective of reconstructing automatically sampled connection subgraphs. Our pretrained model can then be directly applied to target few-shot tasks on without the need for training few-shot tasks. Extensive experiments on real KGs, including NELL, FB15K-237, and ConceptNet, demonstrate the effectiveness of our framework: we show that even a learning-free implementation of CSR can already perform competitively to existing methods on target few-shot tasks; with pretraining, CSR can achieve significant gains of up to 52% on the more challenging inductive few-shot tasks where the entities are also unseen during (pre)training.