Online Knowledge Learning Model Based on Gravitational Field Theory

Currently, low-dimensional embedded representation learning models are the mainstream approach in knowledge representation research, due to ease of calculation and ability to utilize the spatial relationship between knowledge areas, which benefit from static knowledge learning. However, these models...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2019-08, Vol.9 (15), p.3195
Main Authors: Ji, Wenfei, Jiang, Tonghai, Wang, Meng, Tang, Xinyu, Chen, Guang, Yang, Shan
Format: Article
Language:English
Subjects:
Artificial intelligence
Deep learning
Field theory
Graphs
Gravitation theory
gravitational field
Gravitational fields
Gravity
International conferences
Internet
Knowledge bases (artificial intelligence)
knowledge graph
Knowledge representation
knowledge space
Machine learning
Neural networks
online learning
Semantics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently, low-dimensional embedded representation learning models are the mainstream approach in knowledge representation research, due to ease of calculation and ability to utilize the spatial relationship between knowledge areas, which benefit from static knowledge learning. However, these models cannot update and learn knowledge online. Although using update strategies to update the knowledge base has been proposed by some scholars, this still requires retraining of knowledge and does not use the previous learning parameters and models. TransOnLine, an online knowledge learning method based on the theory of gravitational field, inspired by the fact that the forces acting on two objects in a gravitational field are only related to the distances between objects, rebalances the knowledge space caused by new knowledge through dynamic programming via introducing the spatial energy function and energy transfer function to solve the above problems. TransOnLine can reuse the parameters and models of previous learning. Experiments show that the performance of the TransOnLine method is close to state-of-the-art methods, and it is suitable for online learning and updating a relational-intensive knowledge base.
ISSN:2076-3417
2076-3417
DOI:10.3390/app9153195