HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning

TL;DR

HC-GAE introduces a hierarchical clustering-based graph auto-encoder that captures structural features effectively, reduces over-smoothing, and improves graph representation learning for classification tasks.

Contribution

The paper proposes a novel hierarchical clustering approach within GAEs, enabling bidirectional structural feature extraction and addressing over-smoothing issues.

Findings

Effective graph representations for classification tasks.

Reduces over-smoothing in graph convolution.

Demonstrates superior performance on real-world datasets.

Abstract

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing the hard node assignment to decompose a sample graph into a family of separated subgraphs. We compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. On the other hand, during the decoding process, we adopt the soft node assignment to reconstruct the original graph structure by expanding the coarsened nodes. By hierarchically performing the above compressing procedure during the decoding process as well as the expanding procedure during the decoding process, the proposed HC-GAE can effectively extract bidirectionally hierarchical structural features of the original sample graph. Furthermore, we re-design the loss function that can integrate the information from either the encoder or the decoder. Since the associated graph convolution operation of the proposed HC-GAE is restricted in each individual separated subgraph and cannot propagate the node information between different subgraphs, the proposed HC-GAE can significantly reduce the over-smoothing problem arising in the classical convolution-based GAEs. The proposed HC-GAE can generate effective representations for either node classification or graph classification, and the experiments demonstrate the effectiveness on real-world datasets.