Representation Learning Based on Path Selection in Complex Networks

被引：0
|
作者：
Liu Q.-X. [1 ,2 ]
Long H. [2 ]
Zheng P.-X. [3 ]
机构：
[1] Beijing Engineering Applications Research Center on High Volume Language Information Processing and Cloud Computing, Beijing
[2] School of Computer Science and Technology, Beijing Institute of Technology, Beijing
[3] College of Computer Science and Technology, Harbin Engineering University, Harbin, 150001, Heilongjiang
来源：
Long, Hang (2120161020@bit.edu.cn) | 1600年 / Beijing Institute of Technology卷 / 40期
关键词：
Knowledge graph; Path selection; Representation learning;
D O I：
10.15918/j.tbit1001-0645.2018.053
中图分类号：
学科分类号：
摘要：
Path-based and representation-based reasoning are two major methods on knowledge inference. A combination of both algorithms can improve the accuracy of knowledge reasoning. However, there are still some problems, such as inefficiencies in learning, low prediction accuracy and over-fitting of the model. A representation learning method based on path selection was proposed in this paper to further filter the path feature information, to hold the key paths and to use the balance parameter to process the triples of missing path information. In this paper, a public data set was used to test the model. Experiments show that the model can effectively improve the generalization ability and accuracy. © 2020, Editorial Department of Transaction of Beijing Institute of Technology. All right reserved.
引用
收藏
页码：282 / 289
页数：7
相关论文
共 21 条
  • [1] Lao N., Cohen W.W., Relational Retrieval Using a Combination of Path-Constrained Random Walks, (2010)
  • [2] Tong H., Faloutsos C., Pan J.Y., Fast random walk with restart and its applications, International Conference on Data Mining, pp. 613-622, (2006)
  • [3] Lao N., Mitchell T., Cohen W.W., Random walk inference and learning in a large scale knowledge base, Conference on Empirical Methods in Natural Language Processing, pp. 529-539, (2012)
  • [4] Ni L., Cohen W.W., Fast query execution for retrieval models based on path-constrained random walks, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 881-888, (2010)
  • [5] Gardner M., Mitchell T., Efficient and expressive knowledge base completion using subgraph feature extraction, Conference on Empirical Methods in Natural Language Processing, pp. 1488-1498, (2015)
  • [6] Bordes A., Usunier N., Weston J., Et al., Translating embeddings for modeling multi-relational data, International Conference on Neural Information Processing Systems, pp. 2787-2795, (2013)
  • [7] Wang Z., Zhang J., Feng J., Et al., Knowledge graph embedding by translating on hyperplanes, AAAI - Association for the Advancement of Artificial Intelligence, pp. 1112-1119, (2014)
  • [8] Lin Y., Liu Z., Sun M., Et al., Learning entity and relation embeddings for knowledge graph completion, Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 2181-2187, (2015)
  • [9] Guu K., Miller J., Liang P., Traversing knowledge graphs in vector space, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 318-327, (2015)
  • [10] Lin Y., Liu Z., Luan H., Et al., Modeling relationpaths for representation learning of knowledge bases, Computer Science, (2015)
123