Abstract Graph neural networks (GNNs) have seen significant growth in analyzing heterogeneous graphs, which contain different types of nodes and connections. Recent studies have attempted to analyze heterogeneous graphs without relying on manually selected metapaths. However, existing methods often struggle to learn long-range dependencies between distant nodes because of over-squashing and over-smoothing. This paper presents a new approach, type-aligning graph diffusion network (TAGDN), that effectively addresses these challenges. Our main idea is to boost the power of graph diffusion techniques in heterogeneous graphs with a type-adaptive alignment scheme. This approach allows us to exploit long-range dependencies between nodes in heterogeneous graphs without suffering over-squashing and over-smoothing. Through extensive experiments, we show that TAGDN outperforms state-of-the-art heterogeneous GNNs on diverse graph analysis tasks. Ablation studies show that our alignment scheme enhances the capacity of graph diffusion networks in heterogeneous graph analysis, yielding an average improvement of 5.02% in node classification and 25.43% in node clustering. Our implementation is available at https://github.com/SeongJinAhn/TAGDN .

Most Knowledge Graph(KG) embedding models require negative sampling to learn the representations of KG by discriminating the differences between positive and negative triples. Knowledge representation learning tasks such as link prediction are heavily influenced by the quality of negative samples. Despite many attempts, generating high-quality negative samples remains a challenge. In this paper, we propose a novel framework, Bootstrapped Knowledge graph Embedding based on Neighbor Expansion (BKENE), which learns representations of KG without using negative samples. Our model avoids using augmentation methods that can alter the semantic information when creating the two semantically similar views of KG. In particular, we generate an alternative view of KG by aggregating the information of the expanded neighbor of each node with multi-hop relation. Experimental results show that our BKENE outperforms the state-of-the-art methods for link prediction tasks.

Link prediction is one of the key problems for graph-structured data. With the advancement of graph neural networks, graph autoencoders (GAEs) and variational graph autoencoders (VGAEs) have been proposed to learn graph embeddings in an unsupervised way. It has been shown that these methods are effective for link prediction tasks. However, they do not work well in link predictions when a node whose degree is zero (i.g., isolated node) is involved. We have found that GAEs/VGAEs make embeddings of isolated nodes close to zero regardless of their content features. In this paper, we propose a novel Variational Graph Normalized AutoEncoder (VGNAE) that utilize L2-normalization to derive better embeddings for isolated nodes. We show that our VGNAEs outperform the existing state-of-the-art models for link prediction tasks. The code is available at https://github.com/SeongJinAhn/VGNAE.

It is essential to predict the popularity of a particular shop type when investors decide which type of shops to open at a given location.Existing shop-type recommender systems have approached this problem by building a regiontype matrix and analyzing the relationship between different regions and shop types.However, these methods make recommendations for each region, thus having difficulty analyzing a specific shop, especially near the two regions' borders.To tackle this challenge, we propose a novel Graph Neural Network (GNN) model, called GraphShop, to represent shops as nodes in a graph and analyze each shop without assigning it to a region.As it is difficult to find the influential neighbors, we propose two aggregation methods, Distance-Module and TypeModule, in GraphShop.DistanceModule aggregates unordered nearby shops in every zone and filters them from the remote zones.TypeModule reorders the nearby shops based on their types and considers the interaction of different types.Furthermore, to address the lack of open shop-type recommendation datasets, we build a qualitative and large-scale dataset collected from a review website and location-based services.It contains most, if not all, shops in a region and is large and diverse, by containing 53,182 shops with 122 types.Our dataset is available at https://github.com/BoSamothrace/GraphShop.Through the experimental results, we demonstrate that our method outperforms the existing state-of-the-art methods for shoptype recommendation by a factor of up to 37 %.

Most existing algorithms for graph clustering, including SCAN, are not designed to cope with large volumes of data that cannot fit in main memory. When there is not enough memory, those algorithms will incur thrashing, i.e. result in huge I/O costs. We propose an I/O-efficient algorithm for structural clustering, pm-SCAN. The main idea of our scheme is to partition a large graph into several subgraphs that can fit into main memory. We first find clusters in each subgraph, and then merge them to produce final clustering of the input graph. Experimental results show that while other existing algorithms are not scalable to the graph size, our proposed method produces scalable performance for limited memory space.

This paper proposes a cache management scheme for continuous partial match queries in mobile computing systems. Conventional cache management methods for mobile clients are record ID-based ones. However, since the partial match query is a content-based retrieval, the conventional record ID-based approach cannot properly manage the cache consistency. We show the pr edicate- based approach is an effective cache management in mobile environments.