scHyper: reconstructing cell-cell communication through hypergraph neural networks.

Cell-cell communications is crucial for the regulation of cellular life and the establishment of cellular relationships. Most approaches of inferring intercellular communications from single-cell RNA sequencing (scRNA-seq) data lack a comprehensive global network view of multilayered communications. In this context, we propose scHyper, a new method that can infer intercellular communications from a global network perspective and identify the potential impact of all cells, ligand, and receptor expression on the communication score. scHyper designed a new way to represent tripartite relationships, by extracting a heterogeneous hypergraph that includes the source (ligand expression), the target (receptor expression), and the relevant ligand-receptor (L-R) pairs. scHyper is based on hypergraph representation learning, which measures the degree of match between the intrinsic attributes (static embeddings) of nodes and their observed behaviors (dynamic embeddings) in the context (hyperedges), quantifies the probability of forming hyperedges, and thus reconstructs the cell-cell communication score. Additionally, to effectively mine the key mechanisms of signal transmission, we collect a rich dataset of multisubunit complex L-R pairs and propose a nonparametric test to determine significant intercellular communications. Comparing with other tools indicates that scHyper exhibits superior performance and functionality. Experimental results on the human tumor microenvironment and immune cells demonstrate that scHyper offers reliable and unique capabilities for analyzing intercellular communication networks. Therefore, we introduced an effective strategy that can build high-order interaction patterns, surpassing the limitations of most methods that can only handle low-order interactions, thus more accurately interpreting the complexity of intercellular communications.

Enhancing Enterprise Credit Risk Assessment with Cascaded Multi-level Graph Representation Learning.

The assessment of Enterprise Credit Risk (ECR) is a critical technique for investment decisions and financial regulation. Previous methods usually construct enterprise representations by credit-related indicators, such as liquidity and staff quality. However, indicators of many enterprises are not accessible, especially for the small- and medium-sized enterprises. To alleviate the indicator deficiency, graph learning based methods are proposed to enhance enterprise representation learning by the neighbor structure of enterprise graphs. However, existing methods usually only focus on pairwise relationships, and overlook the ubiquitous high-order relationships among enterprises, e.g., supply chain connecting multiple enterprises. To resolve this issue, we propose a Multi-Structure Cascaded Graph Neural Network framework (MS-CGNN) for ECR assessment. It enhances enterprise representation learning based on enterprise graph structures of different granularity, including knowledge graphs of pairwise relationships, homogeneous and heterogeneous hypergraphs of high-order relationships. To distinguish influences of different types of hyperedges, MS-CGNN redefine new type-dependent hyperedge weight matrices for heterogeneous hypergraph convolutions. Experimental results show that MS-CGNN achieves state-of-the-art performance on real-world ECR datasets.

Meta-HGT: Metapath-aware HyperGraph Transformer for heterogeneous information network embedding.

Heterogeneous information network embedding aims to learn low-dimensional node vectors in heterogeneous information networks (HINs), concerning not only structural information but also heterogeneity of diverse node and relation types. Most existing HIN embedding models mainly rely on metapath to define composite relations between node pairs and thus extract substructures from the original HIN. However, due to the pairwise structure of metapath, these models fail to capture the high-order relations (such as "Multiple authors co-authoring a paper") implicitly contained in HINs. To tackle the limitation, this paper proposes a Metapath-aware HyperGraph Transformer (Meta-HGT) for node embedding in HINs. Meta-HGT first extends metapath to guide the high-order relation extraction from original HIN and constructs multiple metapath based hypergraphs with diverse composite semantics. Then, Meta-HGT learns the latent node and hyperedge embeddings in each metapath based hypergraph through Meta-HGT layers. Each layer consists of two types of components, i.e., intra-hyperedge aggregation and inter-hyperedge aggregation, in which a novel type-dependent attention mechanism is proposed for node and hyperedge feature aggregation. Finally, it fuses multiple node embeddings learned from different metapath based hypergraphs via a semantic attention layer and generates the final node embeddings. Extensive experiments have been conducted on three HIN benchmarks for node classification. The results demonstrate that Meta-HGT achieves state-of-the-art performance on all three datasets.