Learning Label Initialization for Time-Dependent Harmonic Extension
This work addresses node classification in graph-based machine learning, but it appears incremental as it builds on existing harmonic extension methods with a time-dependent adaptation.
The paper tackles the problem of node classification on graphs by introducing a time-dependent version of the Dirichlet problem and learning proper initialization for unlabeled nodes, resulting in a solution that matches state-of-the-art methods.
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.