With the development of graph convolutional network (GCN), which is powerful in graph embedding learning meanwhile can capture node feature information, deep multi-view graph clustering methods based on graph autoenco...
详细信息
With the development of graph convolutional network (GCN), which is powerful in graph embedding learning meanwhile can capture node feature information, deep multi-view graph clustering methods based on graph autoencoder have emerged as a new stream. Although they achieve satisfactory performance, they still have the following weaknesses: (1) some of them model the weights for different views in the encoder part by using attention in the multi-view embedding fusion layer, but fail to consider the weighting in the decoder part to measure the contributions of different views to the reconstruction loss. (2) Most of them directly conduct clustering on the multi-view common embedding layer, but fail to guarantee the alignment of clustering results of different views. To this end, we propose a novel GCN-based deep multi-view graph clustering network with weighting mechanism and collaborative training (DMVGC). The model is composed of multiple view-specific graph encoders and a unified graph decoder. Besides the specially-designed attention module in the encoder part, we construct a reconstruction loss with adaptive weighting mechanism in the decoder part. Additionally, a collaborative self-training clustering objective is jointly conducted on each view-specific embedding layer and the common embedding layer, to make the embedding of each view clustering-friendly toward a common partition. Experiments on several datasets demonstrate the effectiveness of our model.
Deep graph clustering, a fundamental yet formidable task in data analysis, aims to partition samples belonging to the same category into their respective clusters. Recently, significant advancements in graph self -sup...
详细信息
Deep graph clustering, a fundamental yet formidable task in data analysis, aims to partition samples belonging to the same category into their respective clusters. Recently, significant advancements in graph self -supervised learning have been made through generative and contrastive learning methods. However, existing methods focus on directly aggregating neighboring node information during the feature extraction stage, thereby neglecting the crucial long-range correlations between nodes. Consequently, non -neighbor node information within the same category remains unexplored, leading to subpar performance in the clustering task. To address this issue, we propose a generative method named Multi -scale graph Clustering Network (MGCN) to learn comprehensive and rich graph representations for deep graph clustering in the feature encoding stage. Specifically, we design a Multi -hop Adaptive Convolutional Module (MACM) integrated into MGCN, which effectively aggregates high -order neighbor node features in each layer of the network. Additionally, we develop an autoencoder to assist MACM in enhancing attribute information, which prevents the node's own features from being overshadowed in the multi -scale feature learning process. Experimental results demonstrate that our proposed MGCN method achieves significantly better clustering performance than existing methods on multiple public datasets.
Hyperspectral image (HSI) clustering is a fundamental yet challenging task that groups image pixels with similar features into distinct clusters. Among various approaches, contrastive learning methods, which employ th...
详细信息
Hyperspectral image (HSI) clustering is a fundamental yet challenging task that groups image pixels with similar features into distinct clusters. Among various approaches, contrastive learning methods, which employ the concept of encouraging semantically similar samples to move closer together while pushing semantically inconsistent samples apart, have garnered significant attention due to their promising performance. However, the most prevalent approaches face two major limitations: 1) treating all samples indiscriminately during optimization, where the abundance of well-categorized samples overwhelms the feature learning process and 2) tending to introduce noise when constructing positive sample pairs through view augmentation or searching the nearest neighbors, which would cause semantic drift of sample features. To solve these issues, we propose a graph autoencoder-based deep clustering framework named spatial-spectral graph contrastive clustering with hard sample mining (SSGCC) that constructs spatial-spectral dual views without data augmentation and focuses more on hard samples rather than treating all samples equally with the aid of spatial-spectral features. Concretely, we extract the spectral features and the neighborhood spatial features of the samples as dual branches to avoid the noise caused by data augmentation and develop the cluster-oriented consistency learning to facilitate the exchange of knowledge between the two spectral-spatial perspectives. In addition, we propose a hard sample mining-based contrastive learning scheme with the aid of spatial-spectral features. To better measure the importance of the samples, we combine spatial features and spectral features to calculate the similarity between sample pairs. The weights of hard sample pairs are dynamically up-weight while the easy ones are down-weighting to improve the discriminative capability. Extensive experiments on four benchmark HSI datasets demonstrate the effectiveness and superiority of
暂无评论