Building Chinese interdisciplinary research centers : the case of Tsinghua University

Abstract

Graph machine learning has been extensively studied in both academia and industry. However, in the literature, most existing graph machine learning models are designed to conduct training with data samples in a random order, which may suffer from suboptimal performance due to ignoring the importance of different graph data samples and their training orders for the model optimization status. To tackle this critical problem, curriculum graph machine learning (Graph CL), which integrates the strength of graph machine learning and curriculum learning, arises and attracts an increasing amount of attention from the research community. Therefore, in this paper, we comprehensively overview approaches on Graph CL and present a detailed survey of recent advances in this direction. Specifically, we first discuss the key challenges of Graph CL and provide its formal problem definition. Then, we categorize and summarize existing methods into three classes based on three kinds of graph machine learning tasks, i.e., node-level, linklevel, and graph-level tasks. Finally, we share our thoughts on future research directions. To the best of our knowledge, this paper is the first survey for curriculum graph machine learning.

Paths for the Digital Transformation and Intelligent Upgrade of China's Discrete Manufacturing Industry

“…Process flow. Multi-variety, small-batch, or single-piece production [1] is adopted according to orders and inventories. The importance is attached to both production and research.…”

“…The manufacturing industry is an economic base, a key to the prosperity of China, and a basis of a strong country [1,2]. As the main body of China's real economy, the manufacturing industry is essential to the national economic system.…”

Reflections on the Development of General Education of University

“…In recent years, general education has been widely emphasized and researched in China's higher education sector, and an early researcher on liberal education is Li Manli, a scholar at the Institute of Education, Tsinghua University. Dr. Li Manli has systematically elaborated on the nature, content and purpose of general education in three dimensions: In terms of purpose, general education aims to produce socially responsible, well-rounded individuals and citizens of the country who are actively involved in the life of society; in nature, general education is the non-vocational and non-professional education that all college students should receive; in terms of content, general education is a broad, non-utilitarian education of basic knowledge, skills and attitudes [3].…”

Detection Probability for Moving Ground Target of Normal Distribution Using an Imaging Satellite

“…Uncertainty is usually measured by using the entropy H(x) measure [12] , According to the theory of probability and mathematical statistics and traffic practice, we may consider the speed and angle of direction of the ground target follow a normal distribution, because a normal distribution has maximum entropy,…”