T- Hop: Tensor representation of paths in graph convolutional networks

TL;DR

This paper introduces T-Hop, a tensor-based method for encoding path information in graphs, which can be integrated into graph convolutional networks to enhance their ability to capture path features.

Contribution

The paper presents a novel tensor representation for graph paths and demonstrates how to incorporate it into existing GCN frameworks like MixHop.

Findings

Tensor encoding of paths improves graph feature representation.

Dimensionality reduction makes tensor computations more feasible.

Integration with MixHop enhances GCN performance.

Abstract

We describe a method for encoding path information in graphs into a 3-d tensor. We show a connection between the introduced path representation scheme and powered adjacency matrices. To alleviate the heavy computational demands of working with the 3-d tensor, we propose to apply dimensionality reduction on the depth axis of the tensor. We then describe our the reduced 3-d matrix can be parlayed into a plausible graph convolutional layer, by infusing it into an established graph convolutional network framework such as MixHop.