3 October 2022 in Expert Systems with Applications
1 January 2022 in Future Generation Computer Systems
9 November 2022 in IEEE Transactions on Knowledge and Data Engineering
Graphs are widely used to model various practical applications. In recent years, graph convolution networks (GCNs) have attracted increasing attention due to the extension of convolution operation from traditional grid data to graph one. However, the representation ability of current GCNs is undoubtedly limited because existing work fails to consider feature interactions. Toward this end, we propose a Dual Feature Interaction-based GCN. Specifically, it models feature interaction in the aspects of 1) node features where we use Newton's identity to extract different-order cross features implicit in the original features and design an attention mechanism to fuse them; and 2) graph convolution where we capture the pairwise interactions among nodes in the neighborhood to expand a weighted sum operation. We evaluate the proposed model with graph data from different fields, and the experimental results on semi-supervised node classification and link prediction demonstrate the effectiveness of the proposed GCN. The data and source codes of this work are available at https://github.com/ZZY-GraphMiningLab/DFI-GCN .
21 March 2022 in IEEE Transactions on Neural Networks and Learning Systems
Graph neural networks (GNNs) have demonstrated great success in many graph data-based applications. The impressive behavior of GNNs typically relies on the availability of a sufficient amount of labeled data for model training. However, in practice, obtaining a large number of annotations is prohibitively labor-intensive and even impossible. Co-training is a popular semi-supervised learning (SSL) paradigm, which trains multiple models based on a common training set while augmenting the limited amount of labeled data used for training each model via the pseudolabeled data generated from the prediction results of other models. Most of the existing co-training works do not control the quality of pseudolabeled data when using them. Therefore, the inaccurate pseudolabels generated by immature models in the early stage of the training process are likely to cause noticeable errors when they are used for augmenting the training data for other models. To address this issue, we propose a self-paced co-training for the GNN (SPC-GNN) framework for semi-supervised node classification. This framework trains multiple GNNs with the same or different structures on different representations of the same training data. Each GNN carries out SSL by using both the originally available labeled data and the augmented pseudolabeled data generated from other GNNs. To control the quality of pseudolabels, a self-paced label augmentation strategy is designed to make the pseudolabels generated at a higher confidence level to be utilized earlier during training such that the negative impact of inaccurate pseudolabels on training data augmentation, and accordingly, the subsequent training process can be mitigated. Finally, each of the trained GNN is evaluated on a validation set, and the best-performing one is chosen as the output. To improve the training effectiveness of the framework, we devise a pretraining followed by a two-step optimization scheme to train GNNs. Experimental results on the node classification task demonstrate that the proposed framework achieves significant improvement over the state-of-the-art SSL methods.
15 March 2023 in Expert Systems with Applications
20 July 2022 in IEEE Transactions on Big Data
Graph Convolution Networks (GCNs) are playing important role and widely used in recommendation systems. This is benefited from their capability of capturing the collaborative signals of higher-order neighbors by exploiting the graph structure. GCN-based methods have made great success in improving recommending performance, but still suffer from the severe problem of data sparsity. An effective solution to alleviate the data sparsity is to introduce attribute information. However, existing GCN-based methods hardly capture the complex attribute information of users and items and the complicated relationships between users, items, and attributes simultaneously. To address the above problems, we propose a novel attribute-fusing graph convolution network model called AF-GCN. Specifically, we first propose an attention-based attribute fusion strategy by taking account of different effects of attributes. Then, we construct a complex graph containing four kinds of nodes. Finally, we design a particular Laplacian matrix, which leverages the attribute information through graph structure to learn user and item representations better. Extensive experimental results on three real-world datasets demonstrate that the proposed AF-GCN significantly outperforms state-of-the-art methods. The source codes of this work are available at https://github.com/xiaorui-mnaire/af-gcn .