Abstract In heterogeneous graph analysis, existing self-supervised learning (SSL) methods face several key challenges. Primarily, these approaches are tailored for node-level tasks and fail to effectively capture global graph-level features, a crucial aspect for comprehensive graph understanding. Furthermore, they predominantly rely on meta-path-based techniques to unravel graph structures, a process that can be computationally intensive and often intractable for complex networks. Another significant limitation is their inability to account for nonpairwise relationships, a common characteristic in real-world networks like protein-protein interaction and collaboration networks, limiting their effectiveness in graph-level learning where high-order connectivity is essential. To address these issues, we propose an innovative SSL framework for heterogeneous hypergraph embedding, expressly designed to enhance graph-level classification. Our framework introduces multi-hop attention in hypergraph convolution, a significant leap from existing attention mechanisms specifically for hypergraphs that primarily focus on immediate neighborhoods. This multi-hop approach allows for an expansive capture of relational structures, both near and far, uncovering intricate patterns integral to accurate graph-level classification. Complementing this, we implement an informative graph-level attentive pooling mechanism that surpasses traditional aggregation methods. It intelligently synthesizes features, taking into account their structural and semantic importance within the hypergraph, thereby preserving critical contextual information. Furthermore, we refine our contrastive learning approach and introduce targeted negative sampling strategies, creating a more robust learning environment that excels at discerning nuanced graph-level features. Rigorous evaluation against established graph kernels, graph neural networks, and graph pooling methods on real-world datasets demonstrates our model’s superior performance, validating its effectiveness in addressing the complexities inherent in heterogeneous graph-level classification.

Session-based recommendations have become increasingly important in social media platforms due to the dynamic and temporal nature of user interactions. The utilization of Graph Neural Networks in these systems has grown due to their proficiency in incorporating node information and structural topology. However, current recommendation methods that use graphs focus on recommendations within a single session, neglecting the more complex dependencies between different sessions. This omission limits improvements in the accuracy of recommendations. In addition, existing GNN-based approaches generally focus on simple binary connections, neglecting to capture the intricate and heterogeneous interactions in real-world situations. Furthermore, a notable obstacle arises from the absence of node positional information for hyperedges in hypergraphs. Therefore, different item orders can lead to identical hyperedges, which limits the formation of precise session vector representations. The paper proposes a unified framework utilizing heterogeneous hypergraph neural networks for session-based social recommendations to address these limitations. This framework utilizes hypergraphs to depict complex multivariate connections among sessions, social networks, and items. It addresses the problem of hyperedge ambiguity while maintaining the sequential order of data. The methodology entails creating a linkage graph and a session-item graph, which aid in identifying similar user intentions across various sessions and potential behavior patterns within a single session. In addition, the framework utilizes a Graph Attention Network (GAT) to combine social information from users and their connections, thereby improving the representation of user interests. Empirical assessments on three datasets show that our proposed model outperforms popular recommendation models. This emphasizes its effectiveness in accurately capturing user preferences and behaviors in session-based social recommendations.

The dynamic and temporal nature of user interactions on social media platforms has increased the importance of session-based recommendations. The adoption of graph neural networks in these systems has increased due to their capacity to incorporate structural topology and node information. Nevertheless, current session-based recommendation methods relying on pairwise graph structure ignore intricate and evolving interactions between users, items, and sessions across domains. However, most methodologies focus on a scenario where consumers interact with a single domain. As a result, they cannot accurately represent the intricate and evolving correlations between users and items in cross-domain scenarios. They consistently face insufficient data because they overlook the fact that users’ behaviors are distributed across domains and sessions. To address these challenges, we propose a novel dynamic hypergraph-based framework for cross-domain session-based social recommendations (DHCSRs). We construct a dynamic heterogeneous hypergraph to model the intricate higher order correlations among inter- and intradomain sessions, items, users, and social networks. In intradomain sessions, the hyperedge incorporates domain-specific features into the embedding process for user embedding by considering product categories. Interdomain sessions capture the complex interests of users who engage with diverse types of content. In addition, the framework utilizes gated recurrent units for user behavior and a domain-driven session-based RNN to capture user and session representations. The domain-driven session-based RNN exchanges information across sessions from various domains in sequential order to ensure alignment of domain interactions. The user behavior RNN learns the user’s global interests and captures behavioral differences across domains. Finally, user behavioral information and session representations are aggregated with the session and item representations from the hypergraph to predict user behavior. Comprehensive experiments demonstrate that the DHCSR model outperforms several baselines across all four datasets, with improvements ranging from 3.56% to 18.31% in HR and from 5.08% to 25.65% in NDCG, significantly enhancing the accuracy of recommendations.

Representation learning in unlabeled heterogeneous graphs has gained significant interest. The heterogeneity in graphs not only provides rich information but also poses challenges to model complex relations in self-supervised learning (SSL) manner. Existing SSL-based approaches are usually designed for node-level tasks and are unable to capture global graph-level features. Also, they often employ computationally expensive meta-path-based techniques, to learn the intrinsic graph structure, that are intractable. Importantly, they overlook non-pairwise relationships among nodes in heterogeneous graphs, for instance in protein-protein interaction networks or collaboration networks, limiting the effectiveness of graph-level learning. To address these issues, we propose a novel self-supervised heterogeneous hypergraph learning framework that captures the richness of heterogeneity, and high-order connectivity in graph-level classification. Unlike traditional methods that rely on meta-path-based approaches to incorporate high-order information, we introduce a k-hop neighborhood strategy to construct intra-graph hyperedges, and a shared attribute-based approach for inter-graph hyperedges to construct the heterogeneous hypergraph. Furthermore, we introduce a context-aware graph-level pooling mechanism that facilitates adaptive aggregation of relevant information across the hypergraph, considering both local and global contexts. Lastly, we design a self-supervised contrastive learning framework by introducing a high-order-aware adaptive augmentation mechanism. This enables the model to learn meaningful graph-level representations from less-labeled data. We evaluate our proposed model against graph kernels, graph neural networks, and graph pooling-based baselines on real-world datasets, demonstrating an overall performance improvement of 5.81% that validates the effectiveness and superiority of the proposed method.

Identifying rising stars is very useful for faster growth of any organization. Rising entities has been explored in academics, sports, and blogs in the recent past, but business side is ignored. However, predicting rising business managers (RBMs) can result in significant business growth of any business. In order to maintain a competitive edge, machine learning techniques should be adopted to devise intelligent business strategies and perform predictions. In this article, RBMs are classified by exploring features of co-business managers (Co-BMs), rather than their own work history. Since ignoring their work history enables such prediction in a cold-start scenario, where work history is not available. After formulating features of Co-BM, the dataset is classified into two different evaluation setups. One is average revenue (AR) and the other one is average relative increase in revenue (ARIR)—class labels. All instances for both labels are randomly sorted into multisize (10, 20, and 30–100) datasets. Later on, these datasets are explored through machine learning classifiers using fivefold cross validation. In order to compare the prediction results with baseline and to measure the effectiveness of the proposed methods, the candidates’ business scores are used, which are calculated by the business definition and formulation. In terms of precision, recall, and f-measure, the feature, category, and model-based experimental results show that the generative models, particularly Bayesian networks, produce better results for an AR-based dataset. Also, overall results show the effective the proposed method.

Although the system for annual rankings of higher education institutions (HEIs) faces considerable criticism, these rankings are here to stay. Having become competent in assigning holistic ranking scores to HEIs, reputed ranking entities have now started focusing on subject-specific and regional rankings. However, in experts’ opinion, the process of assigning rankings should be more consistent, transparent, and representative. This study focuses on enhancing the credibility of the academic ranking process, by performing fine-grained assessment of the academic data pertaining to the computing discipline. The proposed assessment approach explores the data at the sub-discipline level, analyzing several ranking dimensions, including the research productivity, research impact, and research contribution of influential research scholars affiliated with renowned HEIs in the computing discipline. The analysis considers highly curated data published by three well-known international academic ranking entities, namely, Academic Rankings of World Universities (ARWU), Quacquarelli Symonds (QS), and Times Higher Education (THE), in 2018, 2019, and 2020, respectively. Researchers’ profiles are obtained from the Scopus repository, and the DBpedia repository is used to retrieve information about HEIs and their locations. For a stable comparison of the subject-specific academic rankings, the grand average rank measure is employed, whereas for finding the most influential researchers in computing, the ResRank measure is used. The sub-discipline-specific academic rankings provide more detailed insight into the academic rankings, thereby providing more robust decision support. This analysis, which focuses on the computing sub-discipline, is among the first few such efforts.