Abstract: This paper considers a learning framework for ``graph-with-features'' setting, where we are given a graph and associated vector features.The examples of such setting include citation network and chemical molecule.The modern approach to this task is graph neural networks (GNNs). However, due to the nature of GNN architectures, GNNs have several limitations, such as homophilous bias and limited expressive power.Instead of overcoming these limitations, we endeavor an alternative approach to GNNs.Our approach is to obtain a vector representation capturing both features and the graph topology.We then apply standard vector-based learning methods to this representation.For this approach, we propose a simple transformation of features, which we call \textit{ResTran}.We provide theoretical justifications for ResTran from the effective resistance, $k$-means, and spectral clustering points of view.We empirically demonstrate that ResTran is more robust to homophilous bias than established GNN methods.