DNRHP: Temporal Network Representation Learning via Hawkes Point Process.

Graph neural networks (GNNs) have significantly advanced our ability to mine structured data, playing a central role in areas such as social networks and recommendation systems. However, while most GNN-based methods focus on learning node representations in static graphs, they often ignore the dynamic nature of real-world networks, limiting their applicability. Furthermore, existing dynamic representation learning methods using Hawkes point processes, while capable of modeling event sequences, are inherently transductive and tailored to specific scenarios with dual timescales and mixed event types, thus not fully generalizable.

The impact of volunteer service on moral education performance and mental health of college students.

Background: Moral education in colleges and universities is an important part of the talent training system, including moral education curriculum, moral education practice, mental health education. Volunteer service is a public welfare act in which volunteers volunteer their time, knowledge, property, technology, with the ultimate goal of helping others and serving the society without personal compensation. As an innovative form of moral education practice in colleges and universities, college students' voluntary service is of great significance in promoting the reform and innovation of moral education, enhancing the affinity, appeal and influence of moral education, and building a positive psychology for college students.

Multi-Attribute Decision Making with Einstein Aggregation Operators in Complex Q-Rung Orthopair Fuzzy Hypersoft Environments.

The purpose of our research is to extend the formal representation of the human mind to the concept of the complex q-rung orthopair fuzzy hypersoft set (Cq-ROFHSS), a more general hybrid theory. A great deal of imprecision and ambiguity can be captured by it, which is common in human interpretations. It provides a multiparameterized mathematical tool for the order-based fuzzy modeling of contradictory two-dimensional data, which provides a more effective way of expressing time-period problems as well as two-dimensional information within a dataset.

A multi-view contrastive learning for heterogeneous network embedding.

Graph contrastive learning has been developed to learn discriminative node representations on homogeneous graphs. However, it is not clear how to augment the heterogeneous graphs without substantially altering the underlying semantics or how to design appropriate pretext tasks to fully capture the rich semantics preserved in heterogeneous information networks (HINs). Moreover, early investigations demonstrate that contrastive learning suffer from sampling bias, whereas conventional debiasing techniques (e.