Federated recommendation is a new Internet service architecture that aims to provide privacy-preserving recommendation services in federated settings. Existing solutions are used to combine distributed recommendation algorithms and privacy-preserving mechanisms. Thus it inherently takes the form of heavyweight models at the server and hinders the deployment of on-device intelligent models to end-users. This paper proposes a novel Personalized Federated Recommendation (PFedRec) framework to learn many user-specific lightweight models to be deployed on smart devices rather than a heavyweight model on a server. Moreover, we propose a new dual personalization mechanism to effectively learn fine-grained personalization on both users and items. The overall learning process is formulated into a unified federated optimization framework. Specifically, unlike previous methods that share exactly the same item embeddings across users in a federated system, dual personalization allows mild finetuning of item embeddings for each user to generate user-specific views for item representations which can be integrated into existing federated recommendation methods to gain improvements immediately. Experiments on multiple benchmark datasets have demonstrated the effectiveness of PFedRec and the dual personalization mechanism. Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings. The code is available.

The federated recommendation system is an emerging AI service architecture that provides recommendation services in a privacy-preserving manner. Using user-relation graphs to enhance federated recommendations is a promising topic. However, it is still an open challenge to construct the user-relation graph while preserving data locality-based privacy protection in federated settings. Inspired by a simple motivation, similar users share a similar vision (embeddings) to the same item set, this paper proposes a novel Graph-guided Personalization for Federated Recommendation (GPFedRec). The proposed method constructs a user-relation graph from user-specific personalized item embeddings at the server without accessing the users' interaction records. The personalized item embedding is locally fine-tuned on each device, and then a user-relation graph will be constructed by measuring the similarity among client-specific item embeddings. Without accessing users' historical interactions, we embody the data locality-based privacy protection of vanilla federated learning. Furthermore, a graph-guided aggregation mechanism is designed to leverage the user-relation graph and federated optimization framework simultaneously. Extensive experiments on five benchmark datasets demonstrate GPFedRec's superior performance. The in-depth study validates that GPFedRec can generally improve existing federated recommendation methods as a plugin while keeping user privacy safe. Code is available https://github.com/Zhangcx19/GPFedRec

Contact tracking is one of the key technologies in prevention and control of infectious diseases. In the face of a sudden infectious disease outbreak, contact tracking systems can help medical professionals quickly locate and isolate infected persons and high-risk individuals, preventing further spread and a large-scale outbreak of infectious disease. Furthermore, the transmission networks of infectious diseases established using contact tracking technology can aid in the visualization of actual virus transmission paths, which enables simulations and predictions of the transmission process, assessment of the outbreak trend, and further development and deployment of more effective prevention and control strategies. Exploring effective contact tracking methods will be significant. Governments, academics, and industries have all given extensive attention to this goal. In this paper, we review the developments and challenges of current contact tracing technologies regarding individual and group contact from both static and dynamic perspectives, including static individual contact tracing, dynamic individual contact tracing, static group contact tracing, and dynamic group contact tracing. With the purpose of providing useful reference and inspiration for researchers and practitioners in related fields, directions in multi-view contact tracing, multi-scale contact tracing, and AI-based contact tracing are provided for next-generation technologies for epidemic prevention and control.

To help health policy makers gain response time to mitigate infectious disease threats, it is essential to have an efficient epidemic surveillance. One common method of disease surveillance is to carefully select nodes (sentinels, or sensors) in the network to report outbreaks. One would like to choose sentinels so that they discover the outbreak as early as possible. The optimal choice of sentinels depends on the network structure. Studies have addressed this problem for static networks, but this is a first step study to explore designing surveillance systems for early detection on temporal networks. This paper is based on the idea that vaccination strategies can serve as a method to identify sentinels. The vaccination problem is a related question that is much more well studied for temporal networks. To assess the ability to detect epidemic outbreaks early, we calculate the time difference (lead time) between the surveillance set and whole population in reaching 1% prevalence. We find that the optimal selection of sentinels depends on both the network’s temporal structures and the infection probability of the disease. We find that, for a mild infectious disease (low infection probability) on a temporal network in relation to potential disease spreading (the Prostitution network), the strategy of selecting latest contacts of random individuals provide the most amount of lead time. And for a more uniform, synthetic network with community structure the strategy of selecting frequent contacts of random individuals provide the most amount of lead time.