Topology-aware Tensor Decomposition for Meta-graph Learning

TL;DR

This paper introduces TENSUS, a topology-aware tensor decomposition method for meta-graph learning on heterogeneous graphs, improving existing approaches by incorporating topological structure and enhancing performance in node classification and recommendation tasks.

Contribution

The paper proposes a novel topology-aware tensor decomposition method, TENSUS, that captures meta-graph structure and can be integrated into existing heterogeneous graph learning models.

Findings

Significant performance improvements on node classification tasks.

Enhanced recommendation accuracy on heterogeneous graphs.

Effective integration as a plug-in for existing models.

Abstract

Heterogeneous graphs generally refers to graphs with different types of nodes and edges. A common approach for extracting useful information from heterogeneous graphs is to use meta-graphs, which can be seen as a special kind of directed acyclic graph (DAG) with same node and edge types as the heterogeneous graph. However, how to design proper meta-graphs is challenging. Recently, there have been many works on learning suitable meta-graphs from a heterogeneous graph. Existing methods generally introduce continuous weights for edges that are independent of each other, which ignores the topological stucture of meta-graphs and can be ineffective. To address this issue, we propose a new viewpoint from tensor on learning meta-graphs. Such a viewpoint not only helps interpret the limitation of existing works by CANDECOMP/PARAFAC (CP) decomposition, but also inspires us to propose a topology-aware tensor decomposition, called TENSUS, that reflects the structure of DAGs. The proposed topology-aware tensor decomposition is easy to use and simple to implement, and it can be taken as a plug-in part to upgrade many existing works, including node classification and recommendation on heterogeneous graphs. Experimental results on different tasks demonstrate that the proposed method can significantly improve the state-of-the-arts for all these tasks.