One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in underrepresented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning loss functions, can be adopted for enabling graph representation learning models to cope with this challenge. However, these methods often directly operate on the graph representations, ignoring rich discriminative information within the graphs and their interactions. To tackle this issue, we introduce a novel multi-scale oversampling graph neural network (MOSGNN) that learns expressive minority graph representations based on intra- and inter-graph semantics resulting from oversampled graphs at multiple scales - subgraph, graph, and pairwise graphs. It achieves this by jointly optimizing subgraph-level, graph-level, and pairwise-graph learning tasks to learn the discriminative information embedded within and between the minority graphs. Extensive experiments on 16 imbalanced graph datasets show that MOSGNN i) significantly outperforms five state-of-the-art models, and ii) offers a generic framework, in which different advanced imbalanced learning loss functions can be easily plugged in and obtain significantly improved classification performance.

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs, i.e., graphs that are abnormal in their fine-grained (node-level) or holistic (graph-level) properties, respectively. To tackle this challenge we introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations. The random distillation is achieved by training one GNN to predict another GNN with randomly initialized network weights. Extensive experiments on 16 real-world graph datasets from diverse domains show that our model significantly outperforms seven state-of-the-art models. Code and datasets are available at https://git.io/GLocalKD.

Recent interests in graph neural networks (GNNs) have received increasing concerns due to their superior ability in the network embedding field. The GNNs typically follow a message passing scheme and represent nodes by aggregating features from neighbors. However, the current aggregation methods assume that the network structure is static and define the local receptive fields under visible connections, which consequently fails to consider latent or high-order structures. Besides, the aggregation methods are known to have a depth dilemma due to the over-smoothness issues. To solve the above shortcomings, we present in this article a compact graph convolutional network framework which defines the graph receptive fields based on diffusion paths and explicitly compresses the neural networks with sparsity regularization. The proposed model seeks to learn from invisible connections and recover the latent proximity. First, we infer the high-order proximity and construct diffusion paths by diffusion samplings. Compared with random walk samplings, the diffusion samplings are based on regions instead of paths. The network inference then obtains accurate weights that can be leveraged to build small but informative receptive fields with salient neighbors. Second, to utilize the deep information while avoiding overfitting, we propose learning a lightweight model by introducing a nonconvex regularizer. Numerical comparisons with the existing network embedding methods under unsupervised feature learning and supervised classification show the effectiveness of our model.

Deep neural networks (DNNs) has drawn considerable attention in recent years as a result of their remarkable performace in many visual and speech recognition assignments. As the scale of tasks that need to solve is increasingly big, the networks used also become wider and deeper, resulting in millions or even billions of parameters needed. Deep and wide networks with large number of parameters bring many problems, including memory requirement, computation cost and overfitting, which severely hinder the application of DNNs in practice. Therefore, a natural thought is to train sparse networks with less parameters and float operators while maintaining comparable performance. During past few years, a mass of research has been proposed in this area. In this paper, we survey sparsity-promoting techniques in DNNs proposed in recent years. These approaches are roughly divided into three categories, including pruning, randomly reducing the complexity and optimizing with sparse regularizer. Pruning techniques will be introduced first and others will be described in the following section. For each kind of methods, we present approaches in this category, strengths and drawbacks. In the final, we will discuss the relationship of these three categories of methods.