Recommending purely cold-start items is a long-standing and fundamental challenge in the recommender systems. Without any historical interaction on cold-start items, the collaborative filtering (CF) scheme fails to leverage collaborative signals to infer user preference on these items. To solve this problem, extensive studies have been conducted to incorporate side information of items (e.g., content features) into the CF scheme. Specifically, they employ modern neural network techniques (e.g., dropout, consistency constraint) to discover and exploit the coalition effect of content features and collaborative representations. However, we argue that these works less explore the mutual dependencies between content features and collaborative representations and lack sufficient theoretical supports, thus resulting in unsatisfactory performance on cold-start recommendation.In this work, we reformulate the cold-start item representation learning from an information-theoretic standpoint. It aims to maximize the mutual dependencies between item content and collaborative signals. Specifically, the representation learning is theoretically lower-bounded by the integration of two terms: mutual information between collaborative embeddings of users and items, and mutual information between collaborative embeddings and feature representations of items. To model such a learning process, we devise a new objective function founded upon contrastive learning and develop a simple yet efficient Contrastive Learning-based Cold-start Recommendation framework (CLCRec). In particular, CLCRec consists of three components: contrastive pair organization, contrastive embedding, and contrastive optimization modules.
For time-critical precise applications, one popular technology is the real-time precise point positioning (PPP). In recent years, there has been a rapid development in the BeiDou Navigation Satellite System (BDS), and the constellation of global BDS (BDS-3) has been fully deployed. In addition to the regional BDS (BDS-2) constellation, the real-time stream CLK93 has started to support the BDS-3 constellation, indicating that the real-time PPP processing involving BDS-3 observations is feasible. In this study, the global positioning performance of real-time PPP with BDS-3/BDS-2 observations is initially evaluated using the datasets from 147 stations. In the east, north and upward directions, positioning accuracy of 1.8, 1.2 and 2.5 cm in the static mode, and of 6.7, 5.1 and 10.4 cm in the kinematic mode can be achieved for the BDS-3/BDS-2 real-time PPP, respectively, while the corresponding convergence time with a threshold of 10 cm is 32.9, 23.7 and 32.8 min, and 66.9, 42.9 and 69.1 min in the two modes in the three directions, respectively. To complete this, the availability of BDS-3/BDS-2 constellations, the quality of BDS-3/BDS-2 real-time precise satellite products, and the BDS-3/BDS-2 post-processed PPP solutions are also analyzed. For comparison, the results for the GPS are also presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.