Network Vector: Distributed Representations of Networks with Global Context
This work addresses the problem of network analysis for researchers and practitioners by providing a scalable method to compare networks and solve predictive tasks, though it appears incremental as it builds on existing embedding techniques.
The authors tackled the problem of network comparison and predictive tasks by proposing Network Vector, a neural embedding algorithm that learns distributed representations of nodes and entire networks simultaneously, showing effectiveness and efficiency in empirical evaluations.
We propose a neural embedding algorithm called Network Vector, which learns distributed representations of nodes and the entire networks simultaneously. By embedding networks in a low-dimensional space, the algorithm allows us to compare networks in terms of structural similarity and to solve outstanding predictive problems. Unlike alternative approaches that focus on node level features, we learn a continuous global vector that captures each node's global context by maximizing the predictive likelihood of random walk paths in the network. Our algorithm is scalable to real world graphs with many nodes. We evaluate our algorithm on datasets from diverse domains, and compare it with state-of-the-art techniques in node classification, role discovery and concept analogy tasks. The empirical results show the effectiveness and the efficiency of our algorithm.