Drug-drug interactions (DDIs) can critically affect treatment safety and efficacy, especially when multiple drugs are prescribed concurrently. Such interactions may alter pharmacological activity and complicate therapeutic outcomes. Although graph-based learning methods have advanced DDI prediction, most rely solely on drug-drug networks, overlooking valuable information from auxiliary drug-centric networks. To overcome this limitation, it is crucial to adopt more hierarchical strategies that incorporate both drug-drug and auxiliary drug-centric networks to capture nuanced drug representations. In this research, we construct a hierarchical network to incorporate both drug-drug and auxiliary networks as distinct layers and propose a drug-centric hierarchical augmentation method (DCHA) for DDI prediction. DCHA encompasses three core components: a hierarchical learner, a layer discriminator, and a DDI predictor. The hierarchical learner employs a fusion gate to compute augmented drug representations by integrating core drug representations from the drug-drug network and auxiliary representations from other auxiliary drug-centric networks. The layer discriminator helps the hierarchical learner in capturing auxiliary drug representations. With the help of the hierarchical learner and layer discriminator, the DDI predictor finally augments the performance of DDI prediction. Extensive experimentation demonstrates that DCHA outperforms existing state-of-the-art methods in DDI prediction.

The rapid development of heterogeneous networks has proposed new challenges to the long-standing link prediction problem. Existing models trained on the verified edge samples from different types usually learn type-specific knowledge, and their type-specific predictions may be contradictory for unverified edge samples with uncertain types. This challenge is termed edge-type disturbance in link prediction in heterogeneous networks. To address this challenge, we develop a disturbance-resilient prediction method ( DRPM ) comprising a structural characterizer, a type differentiator, and a resilient predictor. The structural characterizer is responsible for learning edge representations for link prediction. Concurrently, the type differentiator distinguishes type-specific edge representations to generate diverse type experts while maximizing their link prediction performances on specific types. Furthermore, the resilient predictor evaluates the reliability weights of different type experts to develop a resilient prediction mechanism to aggregate discriminable predictions. Extensive experiments conducted on various real-world datasets demonstrate the importance of the explainable introduction of the edge-type disturbance and the superiority of DRPM over state-of-the-art methods.

With the growing popularity of artificial intelligence in drug discovery, many deep-learning technologies have been used to automatically predict unknown drug-target interactions (DTIs). A unique challenge in using these technologies to predict DTI is fully exploiting the knowledge diversity across different interaction types, such as drug-drug, drug-target, drug-enzyme, drug-path, and drug-structure types. Unfortunately, existing methods tend to learn the specifical knowledge on each interaction type and they usually ignore the knowledge diversity across different interaction types. Therefore, we propose a multitype perception method (MPM) for DTI prediction by exploiting knowledge diversity across different link types. The method consists of two main components: a type perceptor and a multitype predictor. The type perceptor learns distinguished edge representations by retaining the specifical features across different interaction types; this maximizes the prediction performance for each interaction type. The multitype predictor calculates the type similarity between the type perceptor and predicted interactions, and the domain gate module is reconstructed to assign an adaptive weight to each type perceptor. Extensive experiments demonstrate that our proposed MPM outperforms the state-of-the-art methods in DTI prediction.

Heterogeneous social networks, which are characterized by diverse interaction types, have resulted in new challenges for missing link prediction. Most deep learning models tend to capture type-specific features to maximize the prediction performances on specific link types. However, the types of missing links are uncertain in heterogeneous social networks; this restricts the prediction performances of existing deep learning models. To address this issue, we propose a multi-type transferable method (MTTM) for missing link prediction in heterogeneous social networks, which exploits adversarial neural networks to remain robust against type differences. It comprises a generative predictor and a discriminative classifier. The generative predictor can extract link representations and predict whether the unobserved link is a missing link. To generalize well for different link types to improve the prediction performance, it attempts to deceive the discriminative classifier by learning transferable feature representations among link types. In order not to be deceived, the discriminative classifier attempts to accurately distinguish link types, which indirectly helps the generative predictor judge whether the learned feature representations are transferable among link types. Finally, the integratedMTTMis constructed on this minimax two-player game between the generative predictor and discriminative classifier to predict missing links based on transferable feature representations among link types. Extensive experiments show that the proposedMTTMcan outperform state-of-the-art baselines for missing link prediction in heterogeneous social networks.

As news has become an important way to obtain in-formation, the spread of fake news has caused serious social problems, such as misleading readers and damaging the authority of the government. Therefore, fake news detection has become an important field in social network research. One challenge of fake news detection is how to explore the common latent semantics, which are universally implied in fake news. However, the existing methods are not enough for mining this kind of semantic information. Therefore, we proposed a fake news detection framework named Common Latent Semantics Matching Model (CLSMM), which improves the performance of fake news detection by utilizing common latent semantics in fake news. First, we use BERT model to extract common latent semantics of fake news and use summary generation model to extract distinct latent semantics among each piece of news. Second, we rank the semantic credibility score according to the matching degree of the two kinds of latent semantics mentioned above. Finally, these semantic credibility scores are injected into a fake news classifier to improve the detection performance. Experiments are based on two large scale real-world social media datasets, namely Liar and BuzzFeed. The experimental results show that our model can outperform the accuracy of the state-of-the-art methods by 2.7% and 17.26% on Liar and BuzzFeed, respectively.

Given the distribution difference of the vehicle flow in different urban areas, coordinating the optimization priorities of crossroads in the dynamic control of traffic lights is vital. To reduce traffic congestion at crossroads, in this study, an intelligent diverse optimization priority method (IDOPM) was developed for dynamic traffic light control at crossroads, where diverse optimization priorities can be flexibly and efficiently assigned to different crossroads. The IDOPM mainly consists of a dynamic state constructor and an optimization priority assigner. The dynamic state constructor controls the transformation of the signal combinations of traffic lights. The signal combinations of traffic lights at crossroads are abstracted as cells to be controlled by formulated rules. By designing duration particles and enhancing particles, the optimization priority assigner reconstructs the quantum particle swarm algorithm to assign crossroads with different optimization priorities. The results obtained by comparison with state-of-the-art methods via extensive experiments confirmed the outstanding optimization performance of the proposed IDOPM in dynamic traffic light control.