Semisupervised Learning on Heterogeneous Graphs and its Applications to Facebook News Feed
This addresses the challenge of handling heterogeneous node types in graphs for applications like Facebook News Feed, representing an incremental advancement over existing homogeneous graph methods.
The paper tackled the problem of graph-based semi-supervised learning on heterogeneous graphs, proposing the HELP algorithm, which improved predictive performance in domain classification tasks on a Facebook user-domain interaction graph compared to state-of-the-art methods.
Graph-based semi-supervised learning is a fundamental machine learning problem, and has been well studied. Most studies focus on homogeneous networks (e.g. citation network, friend network). In the present paper, we propose the Heterogeneous Embedding Label Propagation (HELP) algorithm, a graph-based semi-supervised deep learning algorithm, for graphs that are characterized by heterogeneous node types. Empirically, we demonstrate the effectiveness of this method in domain classification tasks with Facebook user-domain interaction graph, and compare the performance of the proposed HELP algorithm with the state of the art algorithms. We show that the HELP algorithm improves the predictive performance across multiple tasks, together with semantically meaningful embedding that are discriminative for downstream classification or regression tasks.