Explore the vast range of titles available.

The paper draws on network theory to employ concepts of homophily and heterophily to investigate whether the presence of familiar, unfamiliar or a mix of actors in an entrepreneurial ecosystem is related to start-up rates. The empirical focus of this study is on 81 UK university entrepreneurial ecosystems and their outputs in terms of academic spinoff companies. The paper finds that university entrepreneurial ecosystems with access to actors of predominantly heterophilious character are associated with higher spinoff start-up rates. It is concluded that in stimulating the development of successful entrepreneurial ecosystems there is a clear need to focus on their openness to heterophilious actors, inclusive of other ecosystems. This is especially important in the context of network lock-in that may arise from dependence on homophilious ties.Plain English SummaryEntrepreneurial ecosystems characterised by openness to diverse actors generate more firms, as shown in a study focusing on 81 UK university entrepreneurial ecosystems. The paper studies network character of actors in entrepreneurial ecosystems and whether this character is associated with start-up rates. Specifically, it focuses on the familiarity of actors, inspecting whether it is related to greater venture formations. In so doing, the study examines 81 UK university entrepreneurial ecosystems. It finds that university entrepreneurial ecosystems that generate more ventures are associated with having a presence of actors of unfamiliar character, drawing attention to the openness of ecosystems’ networks. The key implication of the study is in recognising the link between the ecosystem’s openness to diverse actors and its entrepreneurial performance.

Technological discontinuities pose serious challenges to top managers’ attention. These discontinuities, which often occur at the fringes of an industry, are usually driven by innovative and (often) venture capital-backed start-ups creating new products and transforming existing industries in ways that are difficult for incumbent managers to understand against the backdrop of their existing cognitive schemata. However, failing to appreciate and embrace successful technological discontinuities might endanger incumbents’ very existence. Extending the attention-based view, we explore whether and how interorganizational relationships guide top managers’ attention either to or away from technological discontinuities. We propose that homophilous relationships (e.g., alliances with industry peers) should exhibit a negative relationship with incumbents’ timely attention to technological discontinuities, whereas heterophilous relationships (e.g., with venture capitalists as a result of coinvestments) should exhibit a positive relationship. Furthermore, we hypothesize that the status of the partners strengthens the effect of homophilous and heterophilous relationships with the timely attention of top managers to technological discontinuities. Based on a longitudinal study of the incumbents in four information and communications technology industry sectors, we find that heterophilous ties through corporate venture capital (CVC), coinvesting with high-status venture capital firms, exhibit a strong positive relationship with timely attention. CVC, when it connects senior management to high-status venture capitalists through coinvestments, has a special role in directing top managers’ attention to technological discontinuities and ensuing business opportunities. Implications for the understanding of the role of interorganizational ties as structural determinants of top managers’ attention are discussed.

Accurately predicting the binding affinity between proteins and ligands is crucial for drug discovery. Recent advances in graph neural networks (GNNs) have made significant progress in learning representations of protein-ligand complexes to estimate binding affinities. To improve the performance of GNNs, there frequently needs to look into protein-ligand complexes from geometric perspectives. While the “off-the-shelf” GNNs could incorporate some basic geometric structures of molecules, such as distances and angles, through modeling the complexes as homophilic graphs, these solutions seldom take into account the higher-level geometric attributes like curvatures and homology, and also heterophilic interactions.To address these limitations, we introduce the Curvature-based Adaptive Graph Neural Network (CurvAGN). This GNN comprises two components: a curvature block and an adaptive attention guided neural block (AGN). The curvature block encodes multiscale curvature informaton, then the AGN, based on an adaptive graph attention mechanism, incorporates geometry structure including angle, distance, and multiscale curvature, long-range molecular interactions, and heterophily of the graph into the protein-ligand complex representation. We demonstrate the superiority of our proposed model through experiments conducted on the PDBbind-V2016 core dataset.

Graph-based fraud detection methods have recently attracted much attention due to the rich relational information of graph-structured data, which may facilitate the detection of fraudsters. However, the GNN-based algorithms may exhibit unsatisfactory performance faced with graph heterophily as the fraudsters usually disguise themselves by deliberately making extensive connections to normal users. In addition to this, the class imbalance problem also causes GNNs to overfit normal users and perform poorly for fraudsters. To address these problems, we propose an Imbalanced Graph Structure Learning framework for fraud detection (IGSL for short). Specifically, nodes are picked with a devised multi-relational class-balanced sampler for mini-batch training. Then, an iterative graph structure learning module is proposed to iteratively construct a global homophilic adjacency matrix in the embedding domain. Further, an anchor node message passing mechanism is proposed to reduce the computational complexity of the constructing homophily adjacency matrix. Extensive experiments on benchmark datasets show that IGSL achieves significantly better performance even when the graph is heavily heterophilic and imbalanced.

Millions of people participate in online social media to exchange and share information. Presumably, such information exchange could improve decision making and provide instrumental benefits to the participants. However, to benefit from the information access provided by online social media, the participant will have to overcome the allure of homophily-which refers to the propensity to seek interactions with others of similar status (e.g., religion, education, income, occupation) or values (e.g., attitudes, beliefs, and aspirations). This research assesses the extent to which social media participants exhibit homophily (versus heterophily) in a unique context-virtual investment communities (VICs). We study the propensity of investors in seeking interactions with others with similar sentiments in VICs and identify theoretically important and meaningful conditions under which homophily is attenuated. To address this question, we used a discrete choice model to analyze 682,781 messages on Yahoo! Finance message boards for 29 Dow Jones stocks and assess how investors select a particular thread to respond. Our results revealed that, despite the benefits from heterophily, investors are not immune to the allure of homophily in interactions in VICs. The tendency to exhibit homophily is attenuated by an investor 's experience in VICs, the amount of information in the thread, but amplified by stock volatility. The paper discusses important implications for practice.

Graph neural networks (GNNs) have shown great power in exploring graph representation. However, most current GNNs are based on the homophily assumption and they have two primary weaknesses when applied to heterophily graphs: difficult to capture long-range dependence and unable to distinguish spatial relationships of neighbors. In an attempt to address these issues, we propose a multi-relational neighbors constructed graph neural network (MRN-GNN). Our core components, neighbor reconstruction and the bi-level attention aggregation mechanism, provide an effective way to enhance the ability to express heterophily graphs. Specifically, for neighbor reconstruction, we establish connections between node pairs with highly similar features, making it possible to capture long-range dependences. Meanwhile, we construct multi-relational neighbors for each node to distinguish different spatial structure of neighbors. Based on the reconstructed graph, a bi-level aggregation scheme is proposed to enable hierarchical aggregation, facilitating better feature transmission among multi-relational nodes. During this process, an attention mechanism is built to dynamically assign weights to each neighbor under different relations, further strengthening the representation capability. In this work, we focus on the node classification task on heterophily graphs. We conduct comprehensive experiments on seven datasets, including both heterophily and homophily datasets. Compared with representative methods, our MRN-GNN demonstrates significant superiority on heterophily graphs, while also achieving competitive results on homophily graphs.

The proliferation of robot accounts on social media platforms has posed a significant negative impact, necessitating robust measures to counter network anomalies and safeguard content integrity. Social robot detection has emerged as a pivotal yet intricate task, aimed at mitigating the dissemination of misleading information. While graph-based approaches have attained remarkable performance in this realm, they grapple with a fundamental limitation: the homogeneity assumption in graph convolution allows social robots to stealthily evade detection by mingling with genuine human profiles. To unravel this challenge and thwart the camouflage tactics, this work proposed an innovative social robot detection framework based on enhanced HOmogeneity and Random Forest (HORFBot). At the core of HORFBot lies a homogeneous graph enhancement strategy, intricately woven with edge-removal techniques, to meticulously dissect the graph into multiple revealing subgraphs. Subsequently, leveraging the power of contrastive learning, the proposed methodology meticulously trains multiple graph convolutional networks, each honed to discern nuances within these tailored subgraphs. The culminating stage involves the fusion of these feature-rich base classifiers, harmoniously aggregating their insights to produce a comprehensive detection outcome. Extensive experiments on three social robot detection datasets have shown that this method effectively improves the accuracy of social robot detection and outperforms comparative methods.

Graph Neural Network (GNN) is an effective model for processing graph-structured data. Most GNNs are designed to solve homophilic graphs, where all nodes belong to the same category. However, graph data in real-world applications are mostly heterophilic, and homophilic GNNs cannot handle them well. To address this, we propose a novel hybrid-learning framework based on Node Homophily and Spectral Heterophily (NHSH) for node classification in graph networks. NHSH is designed to achieve state-of-the-art or superior performance on both homophilic and heterophilic graphs. It includes three core modules: homophilic node extraction (HNE), heterophilic spectrum extraction (HSE) and node feature fusion (NFF). More specifically, HNE identifies symmetric neighborhoods of nodes with the same category, extracting local features that reflect these symmetrical structures. Then, HSE uses filters to analyze the high and low-frequency information of nodes in the graph and extract the global features of the nodes. Finally, NFF fuses the above two node features to obtain the final node features in graphs. Moreover, an elaborate loss function drives the network to preserve critical symmetries and structural patterns in the graph. Experiments on eight benchmark datasets validate that NHSH performs comparably or better than existing methods across diverse graph types.

GNN approaches to property valuation typically rely on spatial proximity, assuming that nearby properties exhibit similar price patterns. In practice, this assumption often fails as neighborhood and administrative boundaries create sharp price discontinuities, a form of spatial heterophily. This study proposes a Boundary-Aware Dual-Path Graph Neural Network (BD-GNN), a heterophily-oriented GNN specifically designed for continuous regression tasks. The model uses a dual and adaptive message passing design, separating inter- and intra-boundary pathways and combining them through a learnable gating parameter α. This allows it to capture boundary effects while preserving spatial continuity. Experiments conducted on three structurally contrasting housing datasets, namely Bangkok, King County (USA), and Singapore, demonstrate consistent performance improvements over strong baselines. The proposed BD-GNN reduces MAPE by 7.9%, 4.4%, and 4.5% and increases R2 by 3.2%, 0.7%, and 5.0% for the respective datasets. Beyond predictive performance, α provides a clear picture of how spatial and administrative factors interact across urban scales. GNN Explainer provides local interpretability by showing which neighbors and features shape each prediction. BD-GNN bridges predictive accuracy and structural insight, offering a practical, interpretable framework for applications such as property valuation, taxation, mortgage risk assessment, and urban planning.

The main goal of the analysis presented in this paper is to examine the dynamics of including other-sex peers in the peer networks of early adolescents, aged 11 (at T1) and 13 (at T2), and the relationship between sex heterophily and changes in the sense of peer integration. The analysis was conducted using the Latent Difference Score (LDS) model with data from a representative nationwide longitudinal study in Poland (n = 5748). With reference to the dynamics related to the heterophilic process, the research confirmed that at the beginning of grade 5 of primary school, heterophily is still relatively rare, yet towards the end of early adolescence, there is a gradual shift, more strongly in girls, towards breaking through the strictly same-sex segregation and embarking on heterophilic relationships. Importantly, the LDS model—even when controlling for different measures of peer network—showed significant and positive (among both girls and boys) relations between establishing cross-sex relationships and the sense of peer integration. The results indicate that the appearance of the opposite sex in the peer network between grades 5 and 6 will improve the sense of peer integration. The findings are discussed in relation to results from other studies in the field.