Enhancing Temporal Knowledge Graph Representation with Curriculum Learning
-
Published:2024-08-26
Issue:17
Volume:13
Page:3397
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Liu Yihe1, Shen Yi1, Dai Yuanfei1
Affiliation:
1. College of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, China
Abstract
Temporal knowledge graph representation approaches encounter significant challenges in handling the complex dynamic relations among entities, relations, and time. These challenges include the high difficulty of training and poor generalization performance, particularly with large datasets. To address these issues, this paper introduces curriculum learning strategies from machine learning, aiming to improve learning efficiency through effective curriculum planning. The proposed framework constructs a high-dimensional filtering model based on graph-based high-order receptive fields and employs a scoring model that uses a curriculum temperature strategy to evaluate the difficulty of temporal knowledge graph data quadruples at each stage. By progressively expanding the receptive field and dynamically adjusting the difficulty of learning samples, the model can better understand and capture multi-level information within the graph structure, thereby improving its generalization capabilities. Additionally, a temperature factor is introduced during model training to optimize parameter gradients, alongside a gradually increasing training strategy to reduce training difficulty. Experiments on the benchmark datasets ICEWS14 and ICEWS05-15 demonstrate that this framework not only significantly enhances model performance on these datasets but also substantially reduces training convergence time.
Funder
National Natural Science Foundation of China Natural Science Foundation of Jiangsu Province
Reference33 articles.
1. Chen, K., and Sun, S. (2023, January 7–14). CP-Rec: Contextual prompting for conversational recommender systems. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA. 2. Wang, H., Zhao, M., Xie, X., Li, W., and Guo, M. (2019, January 13–17). Knowledge graph convolutional networks for recommender systems. Proceedings of the World Wide Web Conference, San Francisco, CA, USA. 3. A brief survey of question answering systems;Caballero;Int. J. Artif. Intell. Appl. (IJAIA),2021 4. Huang, X., Zhang, J., Li, D., and Li, P. (2019, January 11–15). Knowledge graph embedding based question answering. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, Melbourne, VIC, Australia. 5. Cai, X., Weng, D., Fu, T., Fu, S., Wang, Y., and Wu, Y. (2024). Linking Text and Visualizations via Contextual Knowledge Graph. IEEE Trans. Vis. Comput. Graph., Early Access.
|
|