张忠元教授及其博士生团队在我校AAA级期刊Information Sciences发表了基于对比聚类集成的GAN聚类性能优化论文。

传统聚类方法尽管取得了显著成效，但其效果往往受制于模型假设。例如，高斯混合模型假定数据源于高斯分布的混合，这使其在符合假设的数据集上表现出色，但在偏离假设的数据集上则显不足。通过将生成对抗网络（Generative Adversarial Network，GAN）融入期望最大化框架，GAN聚类相较于传统方法展现出更大的灵活性和更高的有效性。GAN聚类依赖于通过GAN生成伪标签的合成样本来训练分类器，进而完成簇分配。然而，高质量标记样本的生成是GAN聚类成功的关键，却仍面临诸多挑战。针对上述问题，我们提出了一种新颖的对比网络以及投票机制，用于逐步筛选与融合合成样本的信息，并将其集成到深度聚类框架中，从而结合了GAN聚类与集成学习的优势。通过对多种类型数据集（涵盖图像与非图像）的系统实证分析，我们验证了所提方法在有效性与鲁棒性上的显著优越性。代码已发布于：https://github.com/Jarvisyan/CCEGAN-pytorch。

论文题目： CCEGAN: Enhancing GAN Clustering through Contrastive Clustering Ensemble

论文摘要：Clustering algorithms play a crucial role in various domains, and recent advancements in Generative Adversarial Network (GAN) techniques have opened new possibilities for improving clustering effectiveness. This paper aims to enhance the performance of GAN clustering by addressing the challenge of generating high-quality labeled samples. We propose a novel contrastive network and a voting-based method to progressively filter and fuse information from synthetic samples. These methods are incorporated into a deep clustering ensemble framework, which combines the advantages of GAN clustering and ensemble learning. Through comprehensive empirical analysis on diverse datasets, including both image and non-image datasets, we demonstrate the superiority of our proposed method in terms of effectiveness and robustness. Our approach outperforms existing GAN clustering methods while maintaining a reasonable computational time. This work contributes to the field of clustering algorithms by providing a more effective and robust approach for leveraging GANs in the clustering process. The code is available at https://github.com/Jarvisyan/CCEGAN-pytorch.

撰稿人：张忠元

审稿人：邓露