Graph neural networks (GNNs) have made great progress in graph-based semi-supervised learning (GSSL). However, most existing GNNs are confronted with the oversmoothing issue that limits their expressive ability. A key factor that leads to this problem is the excessive aggregation of information from other classes when updating the node representation. To alleviate this limitation, we propose an effective method called GUIded Dropout over Edges (GUIDE) for training deep GNNs. The core of the method is to reduce the influence of nodes from other classes by removing a certain number of inter-class edges. In GUIDE, we drop edges according to the edge strength, which is defined as the time an edge acts as a bridge along the shortest path between node pairs. We find that the stronger the edge strength, the more likely it is to be an inter-class edge. In this way, GUIDE can drop more inter-class edges and keep more intra-class edges. Therefore, nodes in the same community or class are more similar, whereas different classes are more separated in the embedded space. In addition, we perform some theoretical analysis of the proposed method, which explains why it is effective in alleviating the oversmoothing problem. To validate its rationality and effectiveness, we conduct experiments on six public benchmarks with different GNNs backbones. Experimental results demonstrate that GUIDE consistently outperforms state-of-the-art methods in both shallow and deep GNNs.

Prototypes help to explain the predictions of deep classification models for time series. However, most models learn prototypes by randomly initializing an uncertain number of low-discriminative prototypes, which may lead to unstable models and unreliable results. To address these issues, we propose a new class D iscriminative P rototype L earning Net work (DPL-Net), which learns an appropriate number of class-discriminative prototypes, thus improving classification performance. Specifically, the proposed P rototype I nitialization M echanism (PIM) introduces a new proximity metric based on the silhouette coefficient and statistical metrics. It facilitates the automatic determination of the class-discriminative prototypes for each class. Then, the encoder layer encodes the prototypes derived from PIM and the input series using one-dimensional convolutional neural networks (1D-CNN). Finally, the prototype classification layer optimizes the prototypes according to the regularization terms, while simultaneously classifying the input sequence based on its similarity to the updated prototypes. The comparison experiments are conducted on 26 UCR datasets compared with 10 baselines. The results show that our proposed approach achieves the best accuracy on 11 datasets. Specifically, our method outperforms PIP, CSSL, and LSS by an average of 16.33%, 9.77% and 5.96% on 22, 14 and 16 datasets, respectively. The interpretability experimental results and the application analysis on spectral data indicate that the learned prototypes can provide reasonable explanations for the classification results of the model.

In recent years, multi-view graph clustering algorithms based on representations learning have received extensive attention. However, existing algorithms are still limited in two main aspects, first, most algorithms employ graph convolution networks to learn the local representations, but the presence of high-frequency noise in these representations limits the clustering performance. Second, in the process of constructing a global representation based on the local representations, most algorithms focus on the consistency of each view while ignoring complementarity, resulting in lower representation quality. To address the aforementioned issues, a local-global representation enhancement for multi-view graph clustering algorithm is proposed in this paper. First, the low-frequency signals in the local representations are enhanced by a low-pass graph encoder, which yields smoother and more suitable local representations for clustering. Second, by introducing an attention mechanism, the local embedded representations of each view can be weighted and fused to obtain a global representation. Finally, to enhance the quality of the global representation, it is jointly optimized using the neighborhood contrastive loss and reconstruction loss. The final clustering results are obtained by applying the k-means algorithm to the global representation. A wealth of experiments have validated the effectiveness and robustness of the proposed algorithm.