Node Representation Learning for Directed Graphs
This work addresses the challenge of effectively encoding edge directionality in graph representation learning, which is crucial for applications like social networks and citation graphs, though it appears incremental in improving upon existing directed graph methods.
The authors tackled the problem of learning node representations in directed graphs by proposing a method that maintains separate embedding spaces for source and target roles, using an alternating random walk strategy. They demonstrated consistent outperformance over baselines in node classification and showed robustness across multiple tasks and datasets.
We propose a novel approach for learning node representations in directed graphs, which maintains separate views or embedding spaces for the two distinct node roles induced by the directionality of the edges. We argue that the previous approaches either fail to encode the edge directionality or their encodings cannot be generalized across tasks. With our simple \emph{alternating random walk} strategy, we generate role specific vertex neighborhoods and train node embeddings in their corresponding source/target roles while fully exploiting the semantics of directed graphs. We also unearth the limitations of evaluations on directed graphs in previous works and propose a clear strategy for evaluating link prediction and graph reconstruction in directed graphs. We conduct extensive experiments to showcase our effectiveness on several real-world datasets on link prediction, node classification and graph reconstruction tasks. We show that the embeddings from our approach are indeed robust, generalizable and well performing across multiple kinds of tasks and graphs. We show that we consistently outperform all baselines for node classification task. In addition to providing a theoretical interpretation of our method we also show that we are considerably more robust than the other directed graph approaches.