Recently, Input Mixup, which augments virtual samples by interpolating input features and corresponding labels, is one of the promising methods to alleviate the over-fitting problem on various domains including image classification and natural language processing because of its ability to generate a variety of virtual samples, and ease of usability and versatility. However, designing Input Mixup for the node classification is still challenging due to the irregularity issue that each node contains a different number of neighboring nodes for input and the alignment issue that how to align and interpolate two sets of neighboring nodes is not well-defined when two nodes are interpolated. To address the issues, this paper proposes a novel Mixup method, called iGraphMix, tailored to node classification. Our method generates virtual nodes and their edges by interpolating input features and labels, and attaching sampled neighboring nodes. The virtual graphs generated by iGraphMix serve as inputs for graph neural networks (GNNs) training, thereby facilitating its easy application to various GNNs and enabling effective combination with other augmentation methods. We mathematically prove that training GNNs with iGraphMix leads to better generalization performance compared to that without augmentation, and our experiments support the theoretical findings.

What are the key structures existing in a large real-world MMORPG (Massively Multiplayer Online Role-Playing Game) graph? How can we compactly summarize an MMORPG graph with hierarchical node labels, considering substructures at different levels of hierarchy? Recent MMORPGs generate complex interactions between entities inducing a heterogeneous graph where each entity has hierarchical labels. Succinctly summarizing a heterogeneous MMORPG graph is crucial to better understand its structure; however it is a challenging task since it needs to handle complex interactions and hierarchical labels efficiently. Although there exist few methods to summarize a large-scale graph, they do not deal with heterogeneous graphs with hierarchical node labels.We propose GSHL , a novel method that summarizes a heterogeneous graph with hierarchical labels. We formulate the encoding cost of hierarchical labels using MDL (Minimum Description Length). GSHL exploits the formulation to identify and segment subgraphs, and discovers compact and consistent structures in the graph. Experiments on a large real-world MMORPG graph with multi-million edges show that GSHL is a useful and scalable tool for summarizing the graph, finding important structures in the graph, and finding similar users.

How can we classify graph-structured data only with positive labels? Graph-based positive-unlabeled (PU) learning is to train a binary classifier given only the positive labels when the relationship between examples is given as a graph. The problem is of great importance for various tasks such as detecting malicious accounts in a social network, which are difficult to be modeled by supervised learning when the true negative labels are absent. Previous works for graph-based PU learning assume that the prior distribution of positive nodes is known in advance, which is not true in many real-world cases. In this work, we propose GRAB (Graph-based Risk minimization with iterAtive Belief propagation), a novel end-to-end approach for graph-based PU learning that requires no class prior. GRAB models a given graph as a Markov network and runs the marginalization and update steps iteratively. The marginalization step estimates the marginals of latent variables, while the update step trains a classifier network utilizing the computed priors in the objective function. Extensive experiments on five datasets show that GRAB achieves state-of-the-art accuracy, even compared with previous methods that are given the true prior.