大数据时代下的节点耦合聚类链路预测策略

183 浏览量更新于2024-08-26 收藏 1.98MB PDF 举报

节点耦合聚类的链路预测方法是一篇研究论文，关注于在大数据时代背景下网络中的链接预测问题。随着现实世界网络中潜在信息的重要性日益凸显，链接预测已经成为多个学科领域的研究热点。在大数据的浪潮下，链接预测面临着诸多挑战，包括如何高效地处理大规模数据、如何准确地识别出隐藏的连接模式以及如何应对数据稀疏性等问题。本文的主要贡献在于提出了一种名为"Node-coupling clustering"的方法，这种方法旨在通过节点之间的耦合关系来改进链接预测的精度。传统的链接预测往往依赖于单一的节点属性或者局部结构，而节点耦合聚类则更加强调跨节点间的协同作用，通过挖掘节点之间的共同特征和相互影响，来预测潜在的连接可能性。该方法可能涉及到数据挖掘技术，如协同过滤、社区发现、网络嵌入等，以捕捉网络中的复杂关系。文章流程可能包括以下几个步骤： 1. **背景介绍**：首先概述链接预测的基本概念，以及在大数据环境下其重要性和应用领域，比如社交网络分析、推荐系统和生物网络预测。 2. **方法论**：详细介绍节点耦合聚类算法的原理，可能包括节点特征的选择、聚类过程（如层次聚类、谱聚类或基于图的聚类）、耦合度量的定义以及如何将聚类结果与链接预测相结合。 3. **实验设计**：展示如何在大规模真实网络数据集上实施该方法，并可能对比其他常用的链接预测算法，以评估其性能。 4. **结果与分析**：报告预测结果，分析模型的准确性和鲁棒性，以及对不同参数设置的敏感性分析。 5. **讨论与局限性**：探讨方法的优点和不足，可能涉及可扩展性、计算效率和对噪声数据的处理。 6. **结论与未来工作**：总结研究成果，提出进一步改进或拓展该方法的方向，例如集成更多元的数据源或结合深度学习技术。这篇论文对于理解如何在大数据环境中利用节点耦合聚类进行有效的链路预测具有重要的理论价值和实践意义，为解决实际网络分析中的挑战提供了新的思路和工具。

AUC ¼

H þ 0:5  E

ð2Þ

3.2.2. Precision

This metric considers N links with the highest S

values in all

unknown links. If there are T existing yet unknown links in the

top N unknown links [5,8], the Precision is deﬁned as:

Precision ¼

ð3Þ

4. Node-coupling clustering approaches

In this section, we present our approaches for link prediction.

Firstly, we present a new node-coupling degree metric – node-

coupling clustering coefﬁcient. Then, we present the process of

our approaches. Finally, we give the complexity analysis of our

approaches.

4.1. Node-coupling clustering coefﬁcient

Many similarity-based methods only consider the number or

degrees of common neighbor nodes of a predicted node-pair in link

prediction, and few exploit further the coupling degrees among the

common neighbor nodes and the clustering information to

improve the prediction accuracy. Based on the above reason, we

propose a new node-coupling degree metric – node-coupling clus-

tering coefﬁcient (NCCC), which can capture the clustering infor-

mation of a network and evaluate the coupling degrees between

the common neighbor nodes of a predicted node-pair. It also con-

siders different roles of the common neighbor nodes of a predicted

node-pair in a network. Now, we introduce this metric through a

simple example.

Fig. 1 shows an example for predicting the link between nodes

M and N in two networks. Two original networks are described in

Fig. 1(a) and (b). Fig. 1(c) and (d) are two subgraphs that consist of

nodes M; N and their common neighbors in Fig. 1(a) and (b),

respectively. We aim to predict which link between nodes M and

N is more likely to exist in Fig. 1(a) and (b). In general, we ﬁnd that

the coupling degrees of nodes M; N and their common neighbors

are higher in Fig. 1(c) than (d). Thus, we believe the link of nodes

M; N in Fig. 1(a) is more likely to exist than in Fig. 1(b). If we apply

CN; AA; RA; PA to predict the link of nodes M; N in these two orig-

inal networks, we can gain the same prediction result for each

method. The reasons are as follows: from Fig. 1(a) and (b), we

can see that the common neighbor set fbdf g of nodes M; N are

the same, and every corresponding common neighbor node has

the same degree value in these two original networks. The similar-

ity metric is the number of the common neighbor nodes of a pre-

dicted node-pair in CN. CN has the same prediction results

because of the same common neighbor node set fbdf g of nodes

M; N in these two original networks.

RA; AA are based on the

degree values of the common neighbor nodes. RA has the same

prediction probability as AA because of the same degree value of

every corresponding common neighbor node in fbdf g in these

two original networks. For the same reason, PA provides the same

prediction result because that there are the corresponding same

degree values for nodes M and N in these two original networks.

However, the link probabilities between node M and node N in

Fig. 1(a) and (b) are not likely to be the same.

In the above case, inspired by [10,19], we propose a new node-

coupling degree metric based on the clustering information and

node degree – node-coupling clustering coefﬁcient. This metric

cannot only resolve the above prediction problem in Fig. 1, but also

capture the clustering information of a network. If node n is a com-

mon neighbor node of the predicted node-pair ðM; NÞ, the node-

coupling clustering coefﬁcient of node n; NCCCðnÞ, can be deﬁned

as follows:

NCCCðnÞ¼

i2C

þ CðiÞ



ðnÞ

þ CðjÞ



ð4Þ

where CðnÞ is the neighbor node set of node n. ðM; NÞ denotes a pre-

dicted node-pair. n 2

CðMÞ\CðNÞ. C

denotes the common neigh-

bor node set of the node-pair ðM; NÞ in

CðnÞ, which includes

nodes M; N. Namely C

¼ CðMÞ\CðNÞ\CðnÞ[fM; Ng. d

denotes

the degree value of node i. CðiÞ denotes the clustering coefﬁcient

of node i. In this metric,

þ CðiÞ is considered as the contribution

of node i to the coupling degree of the common neighbor nodes of

the predicted node-pair ðM; NÞ. The node-coupling clustering coefﬁ-

cient of node n is the ratio of the contribution sum of all nodes in C

to that in CðnÞ. In this way, our approaches can apply this metric

that incorporates the clustering information and different roles of

each related node to improve the prediction accuracy for link

prediction.

In Eq. (4), since C

# CðnÞ,

i2C

þ CðiÞ



ðnÞ

þ Cð jÞ



As a result, NCCCðnÞ2ð0; 1. Specially, NCCCðnÞ¼1 when

¼ CðnÞ.

4.2. Node-coupling clustering approach based on probability theory

(NCCPT)

From probability theory, we propose a new link prediction

approach based on the node-coupling clustering coefﬁcient (NCCC)

in Section 4.1. Given a pair of predicted nodes ðx; yÞ, node n is a com-

mon neighbor node of the node-pair ðx; yÞ. NCCCðnÞ can be consid-

ered as the contribution of node n to the connecting probability for

the predicted node-pair ðx; yÞ. PðnÞ denotes the link existence

probability that node x and node y connect because of node n.

PðnÞ

denotes the link non-existence probability that node n

connects node x to node y. Therefore, PðnÞ¼NCCCðnÞ and

PðnÞ¼1  NCCCðnÞ. fA

; A

; ...; A

g is the common neighbor

set of the predicted node-pair ðx; yÞ, namely

CðxÞ\CðyÞ¼

; A

; ...; A

g. We assume that these common neighbor

nodes of the node-pair ðx; yÞ are independent to each other. If there

Fig. 1. An example for predicting the link between nodes M and N in two original networks.

F. Li et al. / Knowledge-Based Systems 89 (2015) 669–680

671

剩余11页未读，继续阅读

weixin_38678057

粉丝: 6
资源: 870

大数据时代下的节点耦合聚类链路预测策略

复杂网络各节点聚类系数和网络平均聚类系数

链路预测代码

复杂网络链路预测.pdf

用python算网络中所有节点的聚类系数的平均值

ucinet计算节点聚类系数

二分网络的聚类系数计算方法

将机器学习分为分类、聚类和预测是按照什么进行的分类，正确吗，每种分类包含哪些常用算法

python如何进行链路预测

python对只有网络结构的网络进行链路预测

最新资源