Journal Article10.48550/arxiv.2310.08917
Relation-aware Ensemble Learning for Knowledge Graph Embedding
Ling Yue,Yongqi Zhang,Quanming Yao,Yong Li,Xian Wu,Ziheng Zhang,Zhenxi Lin,Yefeng Zheng +7 more
TL;DR: A divide-search-combine algorithm RelEns-DSC is proposed that searches the relation-wise ensemble weights independently and has the same computation cost as general ensemble methods but with much better performance.
read more
Abstract: Knowledge graph (KG) embedding is a fundamental task in natural language processing, and various methods have been proposed to explore semantic patterns in distinctive ways. In this paper, we propose to learn an ensemble by leveraging existing methods in a relation-aware manner. However, exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods. To address this issue, we propose a divide-search-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently. This algorithm has the same computation cost as general ensemble methods but with much better performance. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed method in efficiently searching relation-aware ensemble weights and achieving state-of-the-art embedding performance. The code is public at https://github.com/LARS-research/RelEns.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Figure 5: Learning curves of different ensemble methods. RelEns-DSC2/5 indicates the number of threads used for parallel computing. 
Table 4: The pattern modeling and inference abilities of selected score functions. 
Figure 3: An overview of the relation-wise ensemble problem. 
Figure 4: MRR of selected base models for specific relations on the WN18RR dataset. 
Table 5: Statistics of the datasets. 
Table 1: Performance comparison on WN18RR, FB15k-237 and NELL-995 datasets.
Citations
PDEC: A Framework for Improving Knowledge Graph Reasoning Performance through Predicate Decomposition
Yuan Meng
TL;DR: A framework for improving knowledge graph reasoning performance through predicate decomposition effectively addresses predicate polysemy, enhancing reasoning capabilities and improving accuracy.
Relgraph: A Multi-Relational Graph Neural Network Framework for Knowledge Graph Reasoning Based on Relation Graph
Xin Tian,Yuan Meng +1 more
TL;DR: This work introduces Relgraph, a novel KG reasoning framework that introduces relation graphs to explicitly model the interactions between different relations, enabling more comprehensive and accurate handling of representation learning and reasoning tasks on KGs.
References
•Journal Article
Scikit-learn: Machine Learning in Python
Fabian Pedregosa,Gaël Varoquaux,Alexandre Gramfort,Vincent Michel,Bertrand Thirion,Olivier Grisel,Mathieu Blondel,Peter Prettenhofer,Ron Weiss,Vincent Dubourg,Jake Vanderplas,Alexandre Passos,David Cournapeau,Matthieu Brucher,Matthieu Perrot,Edouard Duchesnay +15 more
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
•Proceedings Article
Practical Bayesian Optimization of Machine Learning Algorithms
Jasper Snoek,Hugo Larochelle,Ryan P. Adams +2 more
- 03 Dec 2012
TL;DR: This work describes new algorithms that take into account the variable cost of learning algorithm experiments and that can leverage the presence of multiple cores for parallel experimentation and shows that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization for many algorithms.
Ensemble Methods in Machine Learning
Thomas G. Dietterich
- 21 Jun 2000
TL;DR: Some previous studies comparing ensemble methods are reviewed, and some new experiments are presented to uncover the reasons that Adaboost does not overfit rapidly.
•Proceedings Article
Translating Embeddings for Modeling Multi-relational Data
Antoine Bordes,Nicolas Usunier,Alberto Garcia-Duran,Jason Weston,Oksana Yakhnenko +4 more
- 05 Dec 2013
TL;DR: TransE is proposed, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities, which proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases.
Original Contribution: Stacked generalization
TL;DR: The conclusion is that for almost any real-world generalization problem one should use some version of stacked generalization to minimize the generalization error rate.
7.5K