OFFER: A Motif Dimensional Framework for Network Representation Learning

TL;DR

This paper introduces OFFER, a motif dimensional framework that enhances higher-order graph learning by refining adjacency and transition matrices, leading to improved link prediction and clustering performance.

Contribution

The paper proposes a novel motif dimensional framework that accelerates and improves higher-order graph learning through a two-stage refinement process.

Findings

Enhanced link prediction accuracy

Improved clustering results

Higher efficiency in graph learning algorithms

Abstract

Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results. We apply the acceleration procedure from the dimensional of network motifs. Specifically, the refined degree for nodes and edges are conducted in two stages: (1) employ motif degree of nodes to refine the adjacency matrix of the network; and (2) employ motif degree of edges to refine the transition probability matrix in the learning process. In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined. By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the original algorithms with higher efficiency.