Meta relation-aware Metric Learning Framework for Few-Shot Uncertain Knowledge Graph Completion
- 11 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1-13
Abstract
Uncertainty is a fundamental aspect of human knowledge, widely present in various domains such as medicine, biology, and finance. Uncertain Knowledge Graph Completion (UKGC) tasks encompass both link prediction and confidence prediction. However, the inaccessibility of high-quality knowledge results in sparse knowledge graphs, where a large number of entities exhibit relatively sparse neighborhoods. This sparsity severely hinders the performance of few-shot UKGC models, which generally rely on neighborhood aggregation to enhance entity representations. In this study, we propose a Meta relation-aware Metric learning framework designed for few-shot UKGC, named MMUC. To mitigate neighbor sparsity, MMUC introduces a relation-centric paradigm that decouples representation enhancement from background graphs, integrating an uncertainty-driven similarity measure through a learnable confidence learner to achieve robust, non-linear fusion for joint link and confidence prediction. Extensive evaluations across multiple benchmarks demonstrate MMUC's superior performance through rigorous link and confidence prediction, ablation studies, and sparsity analysis, highlighting its particular resilience to neighbor sparsity in few-shot uncertain KGs. The source code can be accessed in https://github.com/sienna-wxy/MMUC.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (2025JBZX064)
- National Key Research and Development Program of China (2023YFC3502604)
- National Natural Science Foundation of China (82374302)
- Natural Science Foundation of Beijing (L232033)
This publication has 38 references indexed in Scilit:
- Informative relationship multi-task learning: Exploring pairwise contribution across tasks’ sharing knowledgeKnowledge-Based Systems, 2024
- BERT-FKGC: Text-Enhanced Few-Shot Representation Learning for Knowledge Graphs2024
- The STRING database in 2023: protein–protein association networks and functional enrichment analyses for any sequenced genome of interestNucleic Acids Research, 2022
- Gaussian Metric Learning for Few-Shot Uncertain Knowledge Graph Completion2021
- A novel decision-making model for sustainable supply chain finance under uncertainty environmentJournal of Cleaner Production, 2020
- GTransE: Generalizing Translation-Based Model on Uncertain Knowledge Graph Embedding2020
- The need for uncertainty quantification in machine-assisted medical decision makingNature Machine Intelligence, 2019
- Knowledge Graph Embedding: A Survey of Approaches and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2017
- Statistical tests, P values, confidence intervals, and power: a guide to misinterpretationsEuropean Journal of Epidemiology, 2016
- The SIDER database of drugs and side effectsNucleic Acids Research, 2015