English

Learning Label Initialization for Time-Dependent Harmonic Extension

Machine Learning 2022-05-04 v1

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.

Keywords

Cite

@article{arxiv.2205.01358,
  title  = {Learning Label Initialization for Time-Dependent Harmonic Extension},
  author = {Amitoz Azad},
  journal= {arXiv preprint arXiv:2205.01358},
  year   = {2022}
}

Comments

Accepted as a conference paper at IJCAI-2022

R2 v1 2026-06-24T11:05:37.872Z