Learning Label Initialization for Time-Dependent Harmonic Extension
Abstract
Node classification on graphs can be formulated as the Dirichlet problem on graphs where the signal is given at the labeled nodes, and the harmonic extension is done on the unlabeled nodes. This paper considers a time-dependent version of the Dirichlet problem on graphs and shows how to improve its solution by learning the proper initialization vector on the unlabeled nodes. Further, we show that the improved solution is at par with state-of-the-art methods used for node classification. Finally, we conclude this paper by discussing the importance of parameter t, pros, and future directions.
Cite
Text
Azad. "Learning Label Initialization for Time-Dependent Harmonic Extension." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/387Markdown
[Azad. "Learning Label Initialization for Time-Dependent Harmonic Extension." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/azad2022ijcai-learning/) doi:10.24963/IJCAI.2022/387BibTeX
@inproceedings{azad2022ijcai-learning,
title = {{Learning Label Initialization for Time-Dependent Harmonic Extension}},
author = {Azad, Amitoz},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2022},
pages = {2791-2797},
doi = {10.24963/IJCAI.2022/387},
url = {https://mlanthology.org/ijcai/2022/azad2022ijcai-learning/}
}