In recent years, heterogeneous network representation learning has attracted considerable attentions with the consideration of multiple node types. However, most of them ignore the rich set of network attributes (attributed network) and different types of relations (multiplex network), which can hardly recognize the multimodal contextual signals across different relations. While a handful of network embedding techniques are developed for attributed multiplex heterogeneous networks, they are significantly limited to the scalability issue on large-scale network data, due to their heavy computation and memory cost. In this work, we propose a Fast Attributed Multiplex heterogeneous network Embedding framework (FAME) for large-scale network data, by mapping the units from different modalities (i.e., network topological structures, various node features and relations) into the same latent space in an efficient way. Our FAME is an integrative architecture with the scalable spectral transformation and sparse random projection, to automatically preserve both attribute semantics and multi-type relations in the learned embeddings. Extensive experiments on four real-world datasets with various network analytical tasks, demonstrate that FAME achieves both effectiveness and significant efficiency over state-of-the-art baselines. The source code is available at: https://github.com/ZhijunLiu95/FAME. CCS CONCEPTS • Mathematics of computing → Graph algorithms; • Computing methodologies → Learning latent representations.
Firstly aiming at pure agent couldn't construct virtual enterprise process in real-time, the paper puts forward using multi-intelligent-agent virtual enterprise architecture to implement DAE. Secondly with the help of complex data type in BPDL, STR and SOR, the system implements the business process specification and management. And then multiintelligent-agent such as PUA, DRA, RPA, and so on interoperate with each other commonly establishes the dynamic VE WFMS. Finally the paper sums up the merits and faults of this system.
With the developments of sensors in mobile devices, mobile crowdsourcing systems are attracting more and more attention. How to recommend user-preferred and trustful tasks for users is an important issue to improve efficiency of mobile crowdsourcing systems. This paper proposes a novel task recommendation model for mobile crowdsourcing systems. Considering both user similarity and task similarity, the recommendation probabilities of tasks are derived. Based on dwell-time, the latent recommendation probability of tasks can be predicted. In addition, trust of tasks is obtained based on their reputations and participation frequencies. Finally, we perform comprehensive experiments towards the Amazon metadata and YOOCHOOSE data sets to verify the effectiveness of the proposed recommendation model.
Purpose The era of crowd network is coming and the research of its steady-state is of great importance. This paper aims to establish a crowd network simulation platform and maintaining the relative stability of multi-source dissemination systems. Design/methodology/approach With this simulation platform, this paper studies the characteristics of “emergence,” monitors the state of the system and according to the fixed point judges the system of steady-state conditions, then uses three control conditions and control methods to control the system status to acquire general rules for maintain the stability of multi-source information dissemination systems. Findings This paper establishes a novel steady-state maintenance simulation framework. It will be useful for achieving controllability to the evolution of information dissemination and simulating the effectiveness of control conditions for multi-source information dissemination systems. Originality/value This paper will help researchers to solve problems of public opinion control in multi-source information dissemination in crowd network.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.