Node Representation Learning for Directed Graphs

TL;DR

This paper introduces a new method for learning node representations in directed graphs that captures edge directionality through role-specific embeddings and an alternating random walk strategy, improving robustness and performance.

Contribution

The paper presents a novel alternating random walk approach for directed graphs, enabling role-specific embeddings and a comprehensive evaluation strategy for link prediction and graph reconstruction.

Findings

Outperforms all baselines in node classification tasks

Embeddings are robust and generalizable across multiple tasks

Effective in link prediction and graph reconstruction on real-world datasets

Abstract

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.