Rethinking Graph Autoencoder Models for Attributed Graph Clustering

by   Nairouz Mrabah, et al.

Most recent graph clustering methods have resorted to Graph Auto-Encoders (GAEs) to perform joint clustering and embedding learning. However, two critical issues have been overlooked. First, the accumulative error, inflicted by learning with noisy clustering assignments, degrades the effectiveness and robustness of the clustering model. This problem is called Feature Randomness. Second, reconstructing the adjacency matrix sets the model to learn irrelevant similarities for the clustering task. This problem is called Feature Drift. Interestingly, the theoretical relation between the aforementioned problems has not yet been investigated. We study these issues from two aspects: (1) the existence of a trade-off between Feature Randomness and Feature Drift when clustering and reconstruction are performed at the same level, and (2) the problem of Feature Drift is more pronounced for GAE models, compared with vanilla auto-encoder models, due to the graph convolutional operation and the graph decoding design. Motivated by these findings, we reformulate the GAE-based clustering methodology. Our solution is two-fold. First, we propose a sampling operator Ξ that triggers a protection mechanism against the noisy clustering assignments. Second, we propose an operator Υ that triggers a correction mechanism against Feature Drift by gradually transforming the reconstructed graph into a clustering-oriented one. As principal advantages, our solution grants a considerable improvement in clustering effectiveness and robustness and can be easily tailored to existing GAE models.


Embedding Graph Auto-Encoder with Joint Clustering via Adjacency Sharing

Graph convolution networks have attracted many attentions and several gr...

Adversarial Deep Embedded Clustering: on a better trade-off between Feature Randomness and Feature Drift

Clustering using deep autoencoders has been thoroughly investigated in r...

Transforming Graphs for Enhanced Attribute-Based Clustering: An Innovative Graph Transformer Method

Graph Representation Learning (GRL) is an influential methodology, enabl...

Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders

Traditional image clustering methods take a two-step approach, feature l...

Adaptive Graph Auto-Encoder for General Data Clustering

Graph based clustering plays an important role in clustering area. Recen...

Deep Attention-guided Graph Clustering with Dual Self-supervision

Existing deep embedding clustering works only consider the deepest layer...

Auto-encoders for Track Reconstruction in Drift Chambers for CLAS12

In this article we describe the development of machine learning models t...

Please sign up or login with your details

Forgot password? Click here to reset