Click-through Rate (CTR) prediction is a crucial task in online advertising and recommender systems. Theoretically, proper ensemble of multiple different CTR prediction models can improve the prediction effectiveness. Unfortunately, most of the existing ensemble learning methods for CTR prediction are designed for cross-sectional data and neglect user historical behavior sequence which is important for predicting user's future click behavior. To address the above issues, we propose a Hypergraph Diffusion-based Sequential Ensemble framework for CTR prediction (HDSE). Specifically, considering the inherent capability of diffusion models in space exploration, we design a generalized conditional diffusion model, which adaptively identifies critical information from diverse sequential models, to capture user's dynamic interest evolution across diverse contexts. To avoid corrupting the item dependencies caused by isotropic Gaussian noise used in traditional diffusion models, we construct a behavior hypergraph and design an anisotropic hypergraph-based smoothing operator to inject structure-aware noise for better exploring the user's interest space. For large-scale application scenarios, we propose a computationally efficient approximation method for estimating hypergraph propagation matrix in the smoothing operator. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model.

Predicting herb-disease association plays a crucial role in accelerating herb repositioning and expanding clinical applications of Traditional Chinese Medicine (TCM). However, most of the existing methods neglect the fine-grained biomedical information, such as the molecular structures, which leads to inaccurate and incomplete representations of herbs and diseases. Since TCM involves multiple components and modulates various targets, existing methods lack an effective approach to represent these relations, resulting in the omission of critical information. In addition, the lack of interpretability in existing methods limits their credibility and acceptance. To tackle the above problems, we propose a herb-disease association prediction framework, named MVGP, which incorporates Multi-View and multi-Granularity representation learning as well as meta-Path-based relational modeling to accurately capture the relationships between herbs and diseases. Specifically, we design a multi-view learning frame-work that integrates latent information from both TCM and western medicine views. We incorporate fine-grained molecular structures of herbal compounds and target proteins to better characterize features. We design a hypergraph convolutional network to model high-order relations among herbs and compounds, diseases and target proteins. Moreover, we employ meta-path-based relational modeling to make the results interpretable. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed model.

The rapid development of mobile devices applications has put tremendous pressure on edge nodes with limited computing capabilities, which may cause poor user experience. To solve this problem, collaborative cloud-edge computing is proposed. In the cloud-edge computing, an edge node with limited local resources can rent more resources from a cloud node. Since cloud service providers offer a variety of pricing modes for users' different computing demands, edge node needs to select appropriate pricing mode of cloud service and allocates resources between the cloud node and the edge node. It is a sequential decision problem. In this paper, we model it as a Parameterized Action Markov Decision Process, and propose a resource allocation algorithm Cost Efficient Resource Allocation under collaborative Cloud-Edge (CERACE) based on the deep reinforcement learning algorithm Parametrized Deep Q-learning (P-DQN). We evaluate CERACE against three typical resource allocation algorithms Edge First + On Demand (E+O), Edge + Random (E+R) and Random + Random (R+R) based on synthetic data and real data of Google dataset. The experimental results show that CERACE can effectively reduce the long-term operation cost of collaborative cloud-side computing in various demanding settings. Our analysis can provide some useful insights for enterprises to design the resource allocation strategy in the collaborative cloud-side computing system.