Graph neural networks (GNNs), grounded in spatial or spectral domains, have achieved remarkable success in learning graph representations in Euclidean space. Recent advances in spatial GNNs reveal that embedding graph nodes with hierarchical structures into hyperbolic space is more effective, reducing distortion compared to Euclidean embeddings. However, extending spectral GNNs to hyperbolic space remains several challenges, particularly in defining spectral graph convolution and enabling message passing within the hyperbolic geometry. To address these challenges, we propose the hyperbolic graph wavelet neural network (HGWNN), a novel approach for modeling spectral GNNs in hyperbolic space. Specifically, we first define feature transformation and spectral graph wavelet convolution on the hyperboloid manifold using exponential and logarithmic mappings, without increasing model parameter complexity. Moreover, we enable non-linear activation on the Poincaré manifold and efficient message passing via diffeomorphic transformations between the hyperboloid and Poincaré models. Experiments on four benchmark datasets demonstrate the effectiveness of our proposed HGWNN over baseline systems.

Cross-Platform Social Relationship Prediction (CPSRP) aims to utilize users’ data information on multiple platforms to enhance the performance of social relationship prediction, thereby promoting socio-economic development. Due to the highly sensitive nature of users’ data in terms of privacy, CPSRP typically introduces various privacy-preserving mechanisms to safeguard users’ confidential information. Although the introduction mechanism guarantees the security of the users’ private information, it tends to degrade the performance of the social relationship prediction. Additionally, existing social relationship prediction schemes overlook the interdependencies among items invoked in a user behavior sequence. For this purpose, we propose a novel privacy-preserve Federated Social Relationship Prediction with Contrastive Learning framework called FSRPCL, which is a multi-task learning framework based on vertical federated learning. Specifically, the users’ rating information is perturbed with a bounded differential privacy technology, and then the users’ sequential representation information acquired through Transformer is applied for social relationship prediction and contrastive learning. Furthermore, each client uploads their respective weight information to the server, and the server aggregates the weight information and distributes it purposes to each client for updating. Numerous experiments on real-world datasets prove that FSRPCL delivers exceptional performance in social relationship prediction and privacy preservation, and effectively minimizes the impact of privacy-preserving technology on social relationship prediction accuracy.

Event extraction is an important part of natural language information extraction, and it’s widely employed in other natural language processing tasks including question answering and machine reading comprehension. However, there is a lack of recent comprehensive survey papers on event extraction. In the past few years, numerous high-quality and innovative event extraction methods have been proposed, making it necessary to consolidate these new developments with previous work in order to provide a clear overview for researchers and serve as a reference for future studies. In addition, event detection is a fundamental sub-task in event extraction, previous survey papers have often overlooked the related work on event detection. Therefore, this paper aims to bridge these gaps by presenting a comprehensive survey of event extraction, including recent advancements and an analysis of previous research on event detection. The resources for event extraction are first introduced in this research, and then the numerous neural network models currently employed in event extraction tasks are divided into four types: word sequence-based methods, graph-based neural network methods, external knowledge-based approaches, and prompt-based approaches. We compare and contrast them in depth, pointing out the flaws and difficulties with existing research. Finally, we discuss the future of event extraction development.