Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been ...Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.展开更多
In this paper, we will explain the relevance of the starant graphs, graphs created by us in the year of 2002. They were basically circulant graphs with a star graph that connects to all the vertices of the circulant g...In this paper, we will explain the relevance of the starant graphs, graphs created by us in the year of 2002. They were basically circulant graphs with a star graph that connects to all the vertices of the circulant graphs from inside of them, but they did not exist as a separate object of study in the year of 2002, as for all we knew. We now know that they can be used to model even social networking interactions, and they do that job better than any other graph we could be trying to use there. With the development of our mathematical tools, lots of conclusions will be made much more believable and therefore will become much more likely to get support from the relevant industries when attached to new queries.展开更多
自然语言处理是实现人机交互的关键步骤,而汉语自然语言处理(Chinese natural language processing,CNLP)是其中的重要组成部分。随着大模型技术的发展,CNLP进入了一个新的阶段,这些汉语大模型具备更强的泛化能力和更快的任务适应性。然...自然语言处理是实现人机交互的关键步骤,而汉语自然语言处理(Chinese natural language processing,CNLP)是其中的重要组成部分。随着大模型技术的发展,CNLP进入了一个新的阶段,这些汉语大模型具备更强的泛化能力和更快的任务适应性。然而,相较于英语大模型,汉语大模型在逻辑推理和文本理解能力方面仍存在不足。介绍了图神经网络在特定CNLP任务中的优势,进行了量子机器学习在CNLP发展潜力的调查。总结了大模型的基本原理和技术架构,详细整理了大模型评测任务的典型数据集和模型评价指标,评估比较了当前主流的大模型在CNLP任务中的效果。分析了当前CNLP存在的挑战,并对CNLP任务的未来研究方向进行了展望,希望能帮助解决当前CNLP存在的挑战,同时为新方法的提出提供了一定的参考。展开更多
To evaluate transmission rate of highly dynamic space networks,a new method for studying space network capacity is proposed in this paper. Using graph theory,network capacity is defined as the maximum amount of flows ...To evaluate transmission rate of highly dynamic space networks,a new method for studying space network capacity is proposed in this paper. Using graph theory,network capacity is defined as the maximum amount of flows ground stations can receive per unit time. Combined with a hybrid constellation model,network capacity is calculated and further analyzed for practical cases. Simulation results show that network capacity will increase to different extents as link capacity,minimum ground elevation constraint and satellite onboard processing capability change. Considering the efficiency and reliability of communication networks,how to scientifically design satellite networks is also discussed.展开更多
We study a mathematical model of biological neuronal networks composed by any finite number N ≥ 2 of non-necessarily identical cells. The model is a deterministic dynamical system governed by finite-dimensional impul...We study a mathematical model of biological neuronal networks composed by any finite number N ≥ 2 of non-necessarily identical cells. The model is a deterministic dynamical system governed by finite-dimensional impulsive differential equations. The statical structure of the network is described by a directed and weighted graph whose nodes are certain subsets of neurons, and whose edges are the groups of synaptical connections among those subsets. First, we prove that among all the possible networks such as their respective graphs are mutually isomorphic, there exists a dynamical optimum. This optimal network exhibits the richest dynamics: namely, it is capable to show the most diverse set of responses (i.e. orbits in the future) under external stimulus or signals. Second, we prove that all the neurons of a dynamically optimal neuronal network necessarily satisfy Dale’s Principle, i.e. each neuron must be either excitatory or inhibitory, but not mixed. So, Dale’s Principle is a mathematical necessary consequence of a theoretic optimization process of the dynamics of the network. Finally, we prove that Dale’s Principle is not sufficient for the dynamical optimization of the network.展开更多
Both farmers and traders benefit from trade networking, which is crucial for the local economy. Therefore, it is crucial to understand how these networks operate, and how they can be managed more effectively. Througho...Both farmers and traders benefit from trade networking, which is crucial for the local economy. Therefore, it is crucial to understand how these networks operate, and how they can be managed more effectively. Throughout this study, we examine the economic networks formed between farmers and traders through the trade of food products. These networks are analyzed from the perspective of their structure and the factors that influence their development. Using data from 18 farmers and 15 traders, we applied exponential random graph models. The results of our study showed that connectivity, Popularity Spread, activity spread, good transportation systems, and high yields all affected the development of networks. Therefore, farmers’ productivity and high market demand can contribute to local food-crop trade. The network was not affected by reciprocity, open markets, proximity to locations, or trade experience of actors. Policy makers should consider these five factors when formulating policies for local food-crop trade. Additionally, local actors should be encouraged to use these factors to improve their network development. However, it is important to note that these factors alone cannot guarantee success. Policy makers and actors must also consider other factors such as legal frameworks, economic policies, and resource availability. Our approach can be used in future research to determine how traders and farmers can enhance productivity and profit in West Africa. This study addresses a research gap by examining factors influencing local food trade in a developing country.展开更多
为解决目前基于节点采样的图池化方法中所存在的评估节点重要性的策略过于简单以及子结构特征信息大量丢失等问题,提出了基于节点采样的子结构代表层次池化模型(sub-structure representative hierarchical pooling model based on node...为解决目前基于节点采样的图池化方法中所存在的评估节点重要性的策略过于简单以及子结构特征信息大量丢失等问题,提出了基于节点采样的子结构代表层次池化模型(sub-structure representative hierarchical pooling model based on node sampling,SsrPool)。该模型主要包括子结构代表节点选择模块和子结构代表节点特征生成模块2个部分。首先,子结构代表节点选择模块同时考虑了节点特征信息以及结构信息,利用不同方法评估节点重要性并通过不同重要性分数协作产生鲁棒的节点排名以指导节点选择。其次,子结构代表节点特征生成模块通过特征融合保留局部子结构特征信息。通过将SsrPool与现有神经网络相结合,在不同规模公共数据集上的图分类实验结果证明了SsrPool的有效性。展开更多
基金This work was supported by the Kyonggi University Research Grant 2022.
文摘Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.
文摘In this paper, we will explain the relevance of the starant graphs, graphs created by us in the year of 2002. They were basically circulant graphs with a star graph that connects to all the vertices of the circulant graphs from inside of them, but they did not exist as a separate object of study in the year of 2002, as for all we knew. We now know that they can be used to model even social networking interactions, and they do that job better than any other graph we could be trying to use there. With the development of our mathematical tools, lots of conclusions will be made much more believable and therefore will become much more likely to get support from the relevant industries when attached to new queries.
文摘自然语言处理是实现人机交互的关键步骤,而汉语自然语言处理(Chinese natural language processing,CNLP)是其中的重要组成部分。随着大模型技术的发展,CNLP进入了一个新的阶段,这些汉语大模型具备更强的泛化能力和更快的任务适应性。然而,相较于英语大模型,汉语大模型在逻辑推理和文本理解能力方面仍存在不足。介绍了图神经网络在特定CNLP任务中的优势,进行了量子机器学习在CNLP发展潜力的调查。总结了大模型的基本原理和技术架构,详细整理了大模型评测任务的典型数据集和模型评价指标,评估比较了当前主流的大模型在CNLP任务中的效果。分析了当前CNLP存在的挑战,并对CNLP任务的未来研究方向进行了展望,希望能帮助解决当前CNLP存在的挑战,同时为新方法的提出提供了一定的参考。
基金Sponsored by the National Natural Science Foundation of China(Grant No.6137110061001093+6 种基金61401118)the Natural Science Foundation of Shandong Province(Grant No.ZR2014FP016)the Natural Scientific Research Innovation Foundation in Harbin Institute of Technology(Grant No.HIT.NSRIF.2011114HIT.NSRIF.2013136HIT.NSRIF.2016100)the Scientific Research Foundation of Harbin Institute of Technology at Weihai(Grant No.HIT(WH)201409HIT(WH)201410)
文摘To evaluate transmission rate of highly dynamic space networks,a new method for studying space network capacity is proposed in this paper. Using graph theory,network capacity is defined as the maximum amount of flows ground stations can receive per unit time. Combined with a hybrid constellation model,network capacity is calculated and further analyzed for practical cases. Simulation results show that network capacity will increase to different extents as link capacity,minimum ground elevation constraint and satellite onboard processing capability change. Considering the efficiency and reliability of communication networks,how to scientifically design satellite networks is also discussed.
文摘We study a mathematical model of biological neuronal networks composed by any finite number N ≥ 2 of non-necessarily identical cells. The model is a deterministic dynamical system governed by finite-dimensional impulsive differential equations. The statical structure of the network is described by a directed and weighted graph whose nodes are certain subsets of neurons, and whose edges are the groups of synaptical connections among those subsets. First, we prove that among all the possible networks such as their respective graphs are mutually isomorphic, there exists a dynamical optimum. This optimal network exhibits the richest dynamics: namely, it is capable to show the most diverse set of responses (i.e. orbits in the future) under external stimulus or signals. Second, we prove that all the neurons of a dynamically optimal neuronal network necessarily satisfy Dale’s Principle, i.e. each neuron must be either excitatory or inhibitory, but not mixed. So, Dale’s Principle is a mathematical necessary consequence of a theoretic optimization process of the dynamics of the network. Finally, we prove that Dale’s Principle is not sufficient for the dynamical optimization of the network.
文摘Both farmers and traders benefit from trade networking, which is crucial for the local economy. Therefore, it is crucial to understand how these networks operate, and how they can be managed more effectively. Throughout this study, we examine the economic networks formed between farmers and traders through the trade of food products. These networks are analyzed from the perspective of their structure and the factors that influence their development. Using data from 18 farmers and 15 traders, we applied exponential random graph models. The results of our study showed that connectivity, Popularity Spread, activity spread, good transportation systems, and high yields all affected the development of networks. Therefore, farmers’ productivity and high market demand can contribute to local food-crop trade. The network was not affected by reciprocity, open markets, proximity to locations, or trade experience of actors. Policy makers should consider these five factors when formulating policies for local food-crop trade. Additionally, local actors should be encouraged to use these factors to improve their network development. However, it is important to note that these factors alone cannot guarantee success. Policy makers and actors must also consider other factors such as legal frameworks, economic policies, and resource availability. Our approach can be used in future research to determine how traders and farmers can enhance productivity and profit in West Africa. This study addresses a research gap by examining factors influencing local food trade in a developing country.
文摘为解决目前基于节点采样的图池化方法中所存在的评估节点重要性的策略过于简单以及子结构特征信息大量丢失等问题,提出了基于节点采样的子结构代表层次池化模型(sub-structure representative hierarchical pooling model based on node sampling,SsrPool)。该模型主要包括子结构代表节点选择模块和子结构代表节点特征生成模块2个部分。首先,子结构代表节点选择模块同时考虑了节点特征信息以及结构信息,利用不同方法评估节点重要性并通过不同重要性分数协作产生鲁棒的节点排名以指导节点选择。其次,子结构代表节点特征生成模块通过特征融合保留局部子结构特征信息。通过将SsrPool与现有神经网络相结合,在不同规模公共数据集上的图分类实验结果证明了SsrPool的有效性。
