Narrow Results

As a kind of generalization of Transformers in the graph domain, Global Graph Transformers are good at learning distant knowledge by directly doing information interactions on complete graphs, which differs from Local Graph Transformers interacting on the original structures. However, we find that most prior works focus only on graph-level tasks (e.g., graph classification) and few Graph Transformer models can effectively solve node-level tasks, especially semi-supervised node classification, which obviously has important practical significance due to the limitation and expensiveness of these node labels. In order to fill this gap, this paper first summarizes the theoretical advantages of Graph Transformers. And based on some exploring experiments, we give some discussions on the main cause of their poor practical performance in semi-supervised node classifications. Secondly, based on this analysis, we design a three-stage homogeneity augmentation framework and propose a Semi-Global Graph Transformer. Considering both global and local perspectives, the proposed model combines various technologies including self-distillation, pseudo-label filtering, pre-training and fine-tuning, and metric learning. Furthermore, it simultaneously enhances the structure and the optimization, improving its effectiveness, scalability, and generalizability. Finally, extensive experiments on seven public homogeneous and heterophilous graph benchmarks show that the proposed method can achieve competitive or much better results compared to many baseline models including state-of-the-arts.

Graph neural networks (GNNs) have achieved impressive success in various applications. However, training dedicated GNNs for small-scale graphs still faces many problems such as over-fitting and deficiencies in performance improvements. Traditional methods such as data augmentation are commonly used in computer vision (CV) but are barely applied to graph structure data to solve these problems. In this paper, we propose a training framework named MTDA (Multi-Task learning with Data Augmentation)-GNN, which combines data augmentation and multi-task learning to improve the node classification performance of GNN on small-scale graph data. First, we use Graph Auto-Encoders (GAE) as a link predictor, modifying the original graphs’ topological structure by promoting intra-class edges and demoting interclass edges, in this way to denoise the original graph and realize data augmentation. Then the modified graph is used as the input of the node classification model. Besides defining the node pair classification as an auxiliary task, we introduce multi-task learning during the training process, forcing the predicted labels to conform to the observed pairwise relationships and improving the model’s classification ability. In addition, we conduct an adaptive dynamic weighting strategy to distribute the weight of different tasks automatically. Experiments on benchmark data sets demonstrate that the proposed MTDA-GNN outperforms traditional GNNs in graph-based semi-supervised node classification.

The advancement of novel technologies has positioned mobile wireless networks as the central focus of computer technology research. The selection process for the subsequent relay node in message forwarding holds paramount importance and is deemed critical. Drawing inspiration from Social Mobility theory, this paper presents a pioneering node classification model that categorizes all nodes into three distinct types. Furthermore, we introduce the concept of Active Entropy, where the numerical value of Active Entropy serves as a metric for message forwarding. Consequently, the routing algorithm transforms into a limited set of strategies between nodes belonging to different types. This routing algorithm offers numerous advantages including enhanced delivery rate, reduced network overhead ratio and decreased transmission delay. We evaluate and compare the performance of our proposed algorithm with that of DFDL algorithm and Prophet algorithm on the ONE simulation platform. Experimental results demonstrate that our proposed algorithm achieves a delivery rate at least 15% higher compared to the other two algorithms while also reducing overhead ratio.

Graph convolutional networks (GCNs) have achieved great success on graph-structured data. Many GCNs can be considered low-pass filters for graph signals. In this paper, we propose a more powerful GCN, named BiGCN, that extends to bidirectional filtering. Specifically, we consider the original graph structure information and the latent correlation between features. Thus BiGCN can filter the signals along with both the original graph and a latent feature-connection graph. Compared with most existing GCNs, BiGCN is more robust and has powerful capacities for feature denoising. We perform node classification and link prediction in citation networks and co-purchase networks with three settings: Noise-Rate, Noise-Level, and Structure-Mistakes. Extensive experimental results demonstrate that our model outperforms the state-of-the-art graph neural networks in both clean and artificially noisy data.