Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.
Abstract:A large body of evidence demonstrates the key role played by entrepreneurship in promoting economic growth. However, the potential connections between entrepreneurship, social networking, and economic development still require in-depth exploration and discussion. This paper first establishes a theoretical framework combining entrepreneurship capital theory, resource dependence theory and transaction cost theory, then examines the possible associations between entrepreneurship, social networks, and economic growth based on the dynamic panel data model. To achieve the research objectives, the investigators collected data spanning the period between 2007 and 2016 from 31 provinces and cities in China. The authors adopted the enterprise employment rate as a measure of entrepreneurship and used the information sharing rate to assess social networks, which were then both introduced into the economic growth model. Additionally, by using the system of generalized method of moments (GMM) estimation, this article measures the influence of entrepreneurship and social networks on the economic growth of a local area. The empirical results reveal that both entrepreneurship and social networking significantly promote regional economic growth in China. Further, the effect of entrepreneurship is significantly enhanced after introducing the joint effects of entrepreneurship and social network. The findings also expound that entrepreneurship of the eastern zone and social networking of the central section exhibit the strongest potential for economic development of the respective areas. Conversely, entrepreneurship may actually hinder the economic advancement of the central areas of China. Corresponding to the findings, the researchers suggest that it is necessary to devise flexible policies for heterogeneous entrepreneurial environments and to appropriately utilize interpersonal networks to maximize the efficiency of the outputs of economic activity, which are likely to strengthen the role of entrepreneurship and social networks in contemporary economic and business milieu.
To investigate the impact of institutional investors on firms' corporate social responsibility (CSR) engagement while controlling for possible endogeneity concerns, we study how Chinese listed firms adjust their CSR decisions when their institutional investors are distracted by exogenous attention-grabbing events and thus are inattentive. With a sample of Chinese listed firms from 2009 to 2017, we find a significant and robust negative relationship between institutional investor inattention and firms' CSR engagement. This negative relationship is more pronounced for firms with more principal-agent problems and/or weaker corporate governances and is more attributable to the inattention of institutional investors with more monitoring incentives.These findings suggest that managers are less motivated to engage in CSR when they are less monitored by institutional investors, indicating that CSR is beneficial to shareholders of Chinese listed firms. Our findings also indicate that the positive impact of institutional investors on CSR may be constrained by their limited attention.
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.