Degree-Based Random Walk Approach for Graph Embedding

TL;DR

This paper introduces a degree-based random walk sampling method for graph embedding that reduces computational effort by 50% while maintaining accuracy in node classification and link prediction tasks.

Contribution

A novel degree-aware sampling approach for random walks that improves efficiency in graph embedding, especially for large networks.

Findings

Requires 50% less computational effort compared to fixed walk methods.

Maintains similar accuracy in node classification and link prediction.

Effective on large-scale graphs like CORA and CiteSeer.

Abstract

Graph embedding, representing local and global neighborhood information by numerical vectors, is a crucial part of the mathematical modeling of a wide range of real-world systems. Among the embedding algorithms, random walk-based algorithms have proven to be very successful. These algorithms collect information by creating numerous random walks with a redefined number of steps. Creating random walks is the most demanding part of the embedding process. The computation demand increases with the size of the network. Moreover, for real-world networks, considering all nodes on the same footing, the abundance of low-degree nodes creates an imbalanced data problem. In this work, a computationally less intensive and node connectivity aware uniform sampling method is proposed. In the proposed method, the number of random walks is created proportionally with the degree of the node. The advantages of the proposed algorithm become more enhanced when the algorithm is applied to large graphs. A comparative study by using two networks namely CORA and CiteSeer is presented. Comparing with the fixed number of walks case, the proposed method requires 50% less computational effort to reach the same accuracy for node classification and link prediction calculations.