Graph-based recommender system has attracted widespread attention and produced a series of research results. Because of the powerful high-order connection modeling capabilities of the Graph Neural Network, the performance of these graph-based recommender systems are far superior to those of traditional neural network-based collaborative filtering models. However, from both analytical and empirical perspectives, the apparent performance improvement is accompanied with a significant time overhead, which is noticeable in large-scale graph topologies. More importantly, the intrinsic data-sparsity problem substantially limits the performance of graph-based recommender systems, which compelled us to revisit graph-based recommendation from a novel perspective. In this article, we focus on analyzing the time complexity of graph-based recommender systems to make it more suitable for real large-scale application scenarios. We propose a novel end-to-end graph recommendation model called the Collaborative Variational Graph Auto-Encoder (CVGA), which uses the information propagation and aggregation paradigms to encode user–item collaborative relationships on the user–item interaction bipartite graph. These relationships are utilized to infer the probability distribution of user behavior for parameter estimation rather than learning user or item embeddings. By doing so, we reconstruct the whole user–item interaction graph according to the known probability distribution in a feasible and elegant manner. From the perspective of the graph auto-encoder, we convert the graph recommendation task into a graph generation problem and are able to do it with approximately linear time complexity. Extensive experiments on four real-world benchmark datasets demonstrate that CVGA can be trained at a faster speed while maintaining comparable performance over state-of-the-art baselines for graph-based recommendation tasks. Further analysis shows that CVGA can effectively mitigate the data sparsity problem and performs equally well on large-scale datasets.

As enterprises around the globe embrace globalization, strategic alliances among enterprises have become an important means to gain competitive advantages. Enterprises cooperate to improve the quality or lower the prices of their services, which introduce quality correlations, i.e., the quality of a service is associated with other services. Existing approaches for service composition have not fully and systematically considered the quality correlations between services. In this paper, we propose a novel approach named Q2C (Query of Quality Correlation) to systematically model quality correlations and enable efficient queries of quality correlations for service compositions. Given a service composition and a set of candidate services, Q2C first preprocesses the quality correlations among the candidate services and then constructs a quality correlation index graph to enable efficient queries for quality correlations. Extensive experiments are conducted on a real-world web service dataset to demonstrate the effectiveness and efficiency of Q2C.

Currently, Coronavirus Disease 2019 (COVID-19) is still endangering world health and safety and deep learning (DL) is expected to be the most powerful method for efficient detection of COVID-19. However, patients’ privacy concerns prohibit data sharing between medical institutions, leading to unexpected performance of deep neural network (DNN) models. Fortunately, federated learning (FL), as a novel paradigm, allows participating clients to collaboratively train models without exposing source data outside original location. Nevertheless, the current FL-based COVID-19 detection methods prefer optimizing secondary objectives including delay, energy consumption and privacy, while few works focus on improving the model accuracy and stability. In this paper, we propose a federated learning framework with dynamic focus for COVID-19 detection on CXR images, named FedFocus. Specifically, to improve the training efficiency and accuracy, the training loss of each model is taken as the basis for parameter aggregation weights. As training layer deepens, a constantly updated dynamic factor is designed to stabilize the aggregation process. In addition, to highly restore the real dataset, the training sets in our experiments are divided based on the population and the infection of three real cities. Extensive experiments conducted on the real-world CXR images dataset demonstrate that FedFocus outperforms the baselines in model training efficiency, accuracy and stability.

Mobile Edge Computing (MEC), as an emerging and prospective mobile computing paradigm, allows a content provider to serve its users by allocating their mobile devices to nearby edge servers to lower the latency in the delivery of its content to those mobile services. From the content provider's perspective, a cost-effective mobile device allocation (MDA) aims to allocate maximum mobile devices to minimum edge servers. However, the allocation of excessive mobile devices to an edge server may result in severe communication interference and consequently, impact mobile devices data rates. Sometimes, not all users mobile devices can be allocated to edge servers. Unallocated mobile devices can still retrieve content from the remote cloud through base stations, however with high latency. The connection between these mobile devices and the base stations also incur communication interference. We formally model this Interference-aware Mobile Edge Device Allocation (I-MEDA) problem and propose a game-theoretic based approach named I-MEDAGame to formulate the I-MEDA problem as an I-MEDA game. Our theoretical analysis of I-MEDAGame shows that it admits a Nash equilibrium. I-MEDAGame employs a novel decentralized algorithm to find the Nash equilibrium of the IMEDA game. The performance of I-MEDAGame is theoretically analyzed and experimentally evaluated.

Intent modeling has attracted widespread attention in recommender systems. As the core motivation behind user selection of items, intent is crucial for elucidating recommendation results. The current mainstream modeling method is to abstract the intent into unknowable but learnable shared or non-shared parameters. Despite considerable progress, we argue that it still confronts the following challenges: firstly, these methods only capture the coarse-grained aspects of intent, ignoring the fact that user-item interactions will be affected by collective and individual factors (e.g., a user may choose a movie because of its high box office or because of his own unique preferences); secondly, modeling believable intent is severely hampered by implicit feedback, which is incredibly sparse and devoid of true semantics. To address these challenges, we propose a novel recommendation framework designated as Bilateral Intent-guided Graph Collaborative Filtering (BIGCF). Specifically, we take a closer look at user-item interactions from a causal perspective and put forth the concepts of individual intent-which signifies private preferences-and collective intent-which denotes overall awareness. To counter the sparsity of implicit feedback, the feature distributions of users and items are encoded via a Gaussian-based graph generation strategy, and we implement the recommendation process through bilateral intent-guided graph reconstruction re-sampling. Finally, we propose graph contrastive regularization for both interaction and intent spaces to uniformize users, items, intents, and interactions in a self-supervised and non-augmented paradigm. Experimental results on three real-world datasets demonstrate the effectiveness of BIGCF compared with existing solutions.