# CL4KGE: A Curriculum Learning Method for Knowledge Graph Embedding

arXiv: https://arxiv.org/abs/2408.14840 · HTML: https://mlsanity.com/paper/2408.14840/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 64 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 28 of 28)

- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Quaternion Knowledge Graph Embeddings](https://mlsanity.com/paper/1904.10281/) (2019)
- [DKN: Deep Knowledge-Aware Network for News Recommendation](https://mlsanity.com/paper/1801.08284/) (2018)
- [Competence-based Multimodal Curriculum Learning for Medical Report Generation](https://mlsanity.com/paper/2206.14579/) (2022)
- [Curriculum Pre-training for End-to-End Speech Translation](https://mlsanity.com/paper/2004.10093/) (2020)
- [Relation Classification via Recurrent Neural Network](https://mlsanity.com/paper/1508.01006/) (2015)
- [Visualizing and Understanding Curriculum Learning for Long Short-Term Memory Networks](https://mlsanity.com/paper/1611.06204/) (2016)
- [Jointly Learning Explainable Rules for Recommendation with Knowledge Graph](https://mlsanity.com/paper/1903.03714/) (2019)
- [TorusE: Knowledge Graph Embedding on a Lie Group](https://mlsanity.com/paper/1711.05435/) (2017)
- [Theory of Curriculum Learning, with Convex Loss Functions](https://mlsanity.com/paper/1812.03472/) (2018)
- [HousE: Knowledge Graph Embedding with Householder Parameterization](https://mlsanity.com/paper/2202.07919/) (2022)
- [CLNode: Curriculum Learning for Node Classification](https://mlsanity.com/paper/2206.07258/) (2022)
- [Entity Alignment with Noisy Annotations from Large Language Models](https://mlsanity.com/paper/2405.16806/) (2024)
- [Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning](https://mlsanity.com/paper/2206.10140/) (2022)
- [Self-paced ensemble learning for speech and audio classification](https://mlsanity.com/paper/2103.11988/) (2021)
- [Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Tasks](https://mlsanity.com/paper/2008.09377/) (2020)
- [Unsupervised Medical Image Alignment with Curriculum Learning](https://mlsanity.com/paper/2102.10438/) (2021)
- [Automated Curriculum Learning for Embodied Agents: A Neuroevolutionary Approach](https://mlsanity.com/paper/2102.08849/) (2021)
- [Combinatorial Optimization with Automated Graph Neural Networks](https://mlsanity.com/paper/2406.02872/) (2024)
- [MQuinE: a cure for "Z-paradox" in knowledge graph embedding models](https://mlsanity.com/paper/2402.03583/) (2024)
- [Decision-focused Graph Neural Networks for Combinatorial Optimization](https://mlsanity.com/paper/2406.03647/) (2024)

## Abstract (arXiv)

Knowledge graph embedding (KGE) constitutes a foundational task, directed towards learning representations for entities and relations within knowledge graphs (KGs), with the objective of crafting representations comprehensive enough to approximate the logical and symbolic interconnections among entities. In this paper, we define a metric Z-counts to measure the difficulty of training each triple (<head entity, relation, tail entity>) in KGs with theoretical analysis. Based on this metric, we propose CL4KGE, an efficient Curriculum Learning based training strategy for KGE. This method includes a difficulty measurer and a training scheduler that aids in the training of KGE models. Our approach possesses the flexibility to act as a plugin within a wide range of KGE models, with the added advantage of adaptability to the majority of KGs in existence. The proposed method has been evaluated on popular KGE models, and the results demonstrate that it enhances the state-of-the-art methods. The use of Z-counts as a metric has enabled the identification of challenging triples in KGs, which helps in devising effective training strategies.