Adversarial Graph Embedding for Ensemble Clustering

Adversarial Graph Embedding for Ensemble Clustering

Zhiqiang Tao, Hongfu Liu, Jun Li, Zhaowen Wang, Yun Fu

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 3562-3568. https://doi.org/10.24963/ijcai.2019/494

Ensemble clustering generally integrates basic partitions into a consensus one through a graph partitioning method, which, however, has two limitations: 1) it neglects to reuse original features; 2) obtaining consensus partition with learnable graph representations is still under-explored. In this paper, we propose a novel Adversarial Graph Auto-Encoders (AGAE) model to incorporate ensemble clustering into a deep graph embedding process. Specifically, graph convolutional network is adopted as probabilistic encoder to jointly integrate the information from feature content and consensus graph, and a simple inner product layer is used as decoder to reconstruct graph with the encoded latent variables (i.e., embedding representations). Moreover, we develop an adversarial regularizer to guide the network training with an adaptive partition-dependent prior. Experiments on eight real-world datasets are presented to show the effectiveness of AGAE over several state-of-the-art deep embedding and ensemble clustering methods.
Keywords:
Machine Learning: Ensemble Methods
Machine Learning: Unsupervised Learning
Machine Learning: Clustering
Machine Learning: Adversarial Machine Learning