Knowledge representation combining quaternion path integration and depth-wise atrous circular convolution

Xinyuan Chen, Zhongmei Zhou, Meichun Gao, Daya Shi, Mohd N. Husen
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:336-345, 2022.

Abstract

Knowledge models endeavor to improve representation and feature extraction capabilities while keeping low computational cost. Firstly, existing embedding models in hypercomplex spaces of non-Abelian group are optimized. Then a method for fast quaternion multiplication is proposed with proof, with which path semantics are computed and further integrated with the attention mechanism based on the idea semantic extraction of relation sequences could be regarded as a multiple rotational blending problem. A depth-wise atrous circular convolution framework is set up for better feature extraction. Experiments including Link Prediction and Path Query are conducted on benchmark datasets verifying our model holds advantages over state-of-the-art models like Rotate3D. Moreover, the model is tested on a biomedical dataset simulating real-world applications. An ablation study is also performed to explore the effectiveness of different components.

Cite this Paper


BibTeX
@InProceedings{pmlr-v180-chen22c, title = {Knowledge representation combining quaternion path integration and depth-wise atrous circular convolution}, author = {Chen, Xinyuan and Zhou, Zhongmei and Gao, Meichun and Shi, Daya and Husen, Mohd N.}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {336--345}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/chen22c/chen22c.pdf}, url = {https://proceedings.mlr.press/v180/chen22c.html}, abstract = {Knowledge models endeavor to improve representation and feature extraction capabilities while keeping low computational cost. Firstly, existing embedding models in hypercomplex spaces of non-Abelian group are optimized. Then a method for fast quaternion multiplication is proposed with proof, with which path semantics are computed and further integrated with the attention mechanism based on the idea semantic extraction of relation sequences could be regarded as a multiple rotational blending problem. A depth-wise atrous circular convolution framework is set up for better feature extraction. Experiments including Link Prediction and Path Query are conducted on benchmark datasets verifying our model holds advantages over state-of-the-art models like Rotate3D. Moreover, the model is tested on a biomedical dataset simulating real-world applications. An ablation study is also performed to explore the effectiveness of different components. } }
Endnote
%0 Conference Paper %T Knowledge representation combining quaternion path integration and depth-wise atrous circular convolution %A Xinyuan Chen %A Zhongmei Zhou %A Meichun Gao %A Daya Shi %A Mohd N. Husen %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-chen22c %I PMLR %P 336--345 %U https://proceedings.mlr.press/v180/chen22c.html %V 180 %X Knowledge models endeavor to improve representation and feature extraction capabilities while keeping low computational cost. Firstly, existing embedding models in hypercomplex spaces of non-Abelian group are optimized. Then a method for fast quaternion multiplication is proposed with proof, with which path semantics are computed and further integrated with the attention mechanism based on the idea semantic extraction of relation sequences could be regarded as a multiple rotational blending problem. A depth-wise atrous circular convolution framework is set up for better feature extraction. Experiments including Link Prediction and Path Query are conducted on benchmark datasets verifying our model holds advantages over state-of-the-art models like Rotate3D. Moreover, the model is tested on a biomedical dataset simulating real-world applications. An ablation study is also performed to explore the effectiveness of different components.
APA
Chen, X., Zhou, Z., Gao, M., Shi, D. & Husen, M.N.. (2022). Knowledge representation combining quaternion path integration and depth-wise atrous circular convolution. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:336-345 Available from https://proceedings.mlr.press/v180/chen22c.html.

Related Material