scholarly journals Proximity Measures as Graph Convolution Matrices for Link Prediction in Biological Networks

2020 ◽  
Author(s):  
Mustafa Coşkun ◽  
Mehmet Koyutürk
Keyword(s):  
Link Prediction ◽  
Similarity Measures ◽  
Graph Representation ◽  
Supplementary Information ◽  
Great Promise ◽  
Network Embedding ◽  
Common Neighbor ◽  
Node Similarity ◽  
Topological Characteristics ◽  
Low Dimensional

AbstractMotivationLink prediction is an important and well-studied problem in computational biology, with a broad range of applications including disease gene prioritization, drug-disease associations, and drug response in cancer. The general principle in link prediction is to use the topological characteristics and the attributes–if available– of the nodes in the network to predict new links that are likely to emerge/disappear. Recently, graph representation learning methods, which aim to learn a low-dimensional representation of topological characteristics and the attributes of the nodes, have drawn increasing attention to solve the link prediction problem via learnt low-dimensional features. Most prominently, Graph Convolution Network (GCN)-based network embedding methods have demonstrated great promise in link prediction due to their ability of capturing non-linear information of the network. To date, GCN-based network embedding algorithms utilize a Laplacian matrix in their convolution layers as the convolution matrix and the effect of the convolution matrix on algorithm performance has not been comprehensively characterized in the context of link prediction in biomedical networks. On the other hand, for a variety of biomedical link prediction tasks, traditional node similarity measures such as Common Neighbor, Ademic-Adar, and other have shown promising results, and hence there is a need to systematically evaluate the node similarity measures as convolution matrices in terms of their usability and potential to further the state-of-the-art.ResultsWe select 8 representative node similarity measures as convolution matrices within the single-layered GCN graph embedding method and conduct a systematic comparison on 3 important biomedical link prediction tasks: drug-disease association (DDA) prediction, drug–drug interaction (DDI) prediction, protein–protein interaction (PPI) prediction. Our experimental results demonstrate that the node similarity-based convolution matrices significantly improves GCN-based embedding algorithms and deserve more attention in the future biomedical link predictionAvailabilityOur method is implemented as a python library and is available at [email protected] informationSupplementary data are available at Bioinformatics online.

SIMILARITY INDEX BASED ON THE INFORMATION OF NEIGHBOR NODES FOR LINK PREDICTION OF COMPLEX NETWORK

2013 ◽  
Vol 27 (06) ◽  
pp. 1350039 ◽  
Author(s):  
JING WANG ◽  
LILI RONG
Keyword(s):  
Link Prediction ◽  
High Efficiency ◽  
Similarity Index ◽  
Similarity Measures ◽  
Nearest Neighbors ◽  
Clustering Coefficient ◽  
Local Similarity ◽  
Common Neighbor ◽  
Similarity Indices ◽  
Node Similarity

Link prediction in complex networks has attracted much attention recently. Many local similarity measures based on the measurements of node similarity have been proposed. Among these local similarity indices, the neighborhood-based indices Common Neighbors (CN), Adamic-Adar (AA) and Resource Allocation (RA) index perform best. It is found that the node similarity indices required only information on the nearest neighbors are assigned high scores and have very low computational complexity. In this paper, a new index based on the contribution of common neighbor nodes to edges is proposed and shown to have competitively good or even better prediction than other neighborhood-based indices especially for the network with low clustering coefficient with its high efficiency and simplicity.

scholarly journals Semisupervised Community Preserving Network Embedding with Pairwise Constraints

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Dong Liu ◽  
Yan Ru ◽  
Qinpeng Li ◽  
Shibin Wang ◽  
Jianwei Niu
Keyword(s):  
Community Structure ◽  
Link Prediction ◽  
Learning Algorithms ◽  
Nonnegative Matrix ◽  
Machine Learning Algorithms ◽  
Network Visualization ◽  
Network Embedding ◽  
Pairwise Constraints ◽  
Node Clustering ◽  
Low Dimensional

Network embedding aims to learn the low-dimensional representations of nodes in networks. It preserves the structure and internal attributes of the networks while representing nodes as low-dimensional dense real-valued vectors. These vectors are used as inputs of machine learning algorithms for network analysis tasks such as node clustering, classification, link prediction, and network visualization. The network embedding algorithms, which considered the community structure, impose a higher level of constraint on the similarity of nodes, and they make the learned node embedding results more discriminative. However, the existing network representation learning algorithms are mostly unsupervised models; the pairwise constraint information, which represents community membership, is not effectively utilized to obtain node embedding results that are more consistent with prior knowledge. This paper proposes a semisupervised modularized nonnegative matrix factorization model, SMNMF, while preserving the community structure for network embedding; the pairwise constraints (must-link and cannot-link) information are effectively fused with the adjacency matrix and node similarity matrix of the network so that the node representations learned by the model are more interpretable. Experimental results on eight real network datasets show that, comparing with the representative network embedding methods, the node representations learned after incorporating the pairwise constraints can obtain higher accuracy in node clustering task and the results of link prediction, and network visualization tasks indicate that the semisupervised model SMNMF is more discriminative than unsupervised ones.

scholarly journals GLEE: Geometric Laplacian Eigenmap Embedding

2020 ◽  
Vol 8 (2) ◽  
Author(s):  
Leo Torres ◽  
Kevin S Chan ◽  
Tina Eliassi-Rad
Keyword(s):  
Link Prediction ◽  
Graph Embedding ◽  
Laplacian Matrix ◽  
Dimensional Representation ◽  
Laplacian Eigenmaps ◽  
New Approach ◽  
Graph Reconstruction ◽  
Node Similarity ◽  
Distance Minimization ◽  
Low Dimensional

Abstract Graph embedding seeks to build a low-dimensional representation of a graph $G$. This low-dimensional representation is then used for various downstream tasks. One popular approach is Laplacian Eigenmaps (LE), which constructs a graph embedding based on the spectral properties of the Laplacian matrix of $G$. The intuition behind it, and many other embedding techniques, is that the embedding of a graph must respect node similarity: similar nodes must have embeddings that are close to one another. Here, we dispose of this distance-minimization assumption. Instead, we use the Laplacian matrix to find an embedding with geometric properties instead of spectral ones, by leveraging the so-called simplex geometry of $G$. We introduce a new approach, Geometric Laplacian Eigenmap Embedding, and demonstrate that it outperforms various other techniques (including LE) in the tasks of graph reconstruction and link prediction.

scholarly journals Learning Network Embedding with Community Structural Information

2019 ◽  
Author(s):  
Yu Li ◽  
Ying Wang ◽  
Tingting Zhang ◽  
Jiawei Zhang ◽  
Yi Chang
Keyword(s):  
Community Structure ◽  
Link Prediction ◽  
Structural Information ◽  
Representation Learning ◽  
Network Embedding ◽  
Learning Network ◽  
Optimization Framework ◽  
Vertex Representation ◽  
Low Dimensional ◽  
Embedding Methods

Network embedding is an effective approach to learn the low-dimensional representations of vertices in networks, aiming to capture and preserve the structure and inherent properties of networks. The vast majority of existing network embedding methods exclusively focus on vertex proximity of networks, while ignoring the network internal community structure. However, the homophily principle indicates that vertices within the same community are more similar to each other than those from different communities, thus vertices within the same community should have similar vertex representations. Motivated by this, we propose a novel network embedding framework NECS to learn the Network Embedding with Community Structural information, which preserves the high-order proximity and incorporates the community structure in vertex representation learning. We formulate the problem into a principled optimization framework and provide an effective alternating algorithm to solve it. Extensive experimental results on several benchmark network datasets demonstrate the effectiveness of the proposed framework in various network analysis tasks including network reconstruction, link prediction and vertex classification.

Link prediction based on local community properties

2016 ◽  
Vol 30 (31) ◽  
pp. 1650222 ◽  
Author(s):  
Xu-Hua Yang ◽  
Hai-Feng Zhang ◽  
Fei Ling ◽  
Zhi Cheng ◽  
Guo-Qing Weng ◽  
...  
Keyword(s):  
Link Prediction ◽  
Local Community ◽  
Network Evolution ◽  
Clustering Coefficient ◽  
Prediction Algorithm ◽  
Node Degree ◽  
Common Neighbor ◽  
Node Similarity ◽  
The Common ◽  
Edge Clustering Coefficient

The link prediction algorithm is one of the key technologies to reveal the inherent rule of network evolution. This paper proposes a novel link prediction algorithm based on the properties of the local community, which is composed of the common neighbor nodes of any two nodes in the network and the links between these nodes. By referring to the node degree and the condition of assortativity or disassortativity in a network, we comprehensively consider the effect of the shortest path and edge clustering coefficient within the local community on node similarity. We numerically show the proposed method provide good link prediction results.

scholarly journals Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Prediction

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Chuanting Zhang ◽  
Ke-Ke Shang ◽  
Jingping Qiao
Keyword(s):  
Link Prediction ◽  
Graph Mining ◽  
Data Science ◽  
Fundamental Problem ◽  
Structural Features ◽  
Similarity Function ◽  
Network Embedding ◽  
Feature Representations ◽  
Node Similarity ◽  
Edge Features

Link prediction is a fundamental problem of data science, which usually calls for unfolding the mechanisms that govern the micro-dynamics of networks. In this regard, using features obtained from network embedding for predicting links has drawn widespread attention. Although methods based on edge features or node similarity have been proposed to solve the link prediction problem, many technical challenges still exist due to the unique structural properties of networks, especially when the networks are sparse. From the graph mining perspective, we first give empirical evidence of the inconsistency between heuristic and learned edge features. Then, we propose a novel link prediction framework, AdaSim, by introducing an Adaptive Similarity function using features obtained from network embedding based on random walks. The node feature representations are obtained by optimizing a graph-based objective function. Instead of generating edge features using binary operators, we perform link prediction solely leveraging the node features of the network. We define a flexible similarity function with one tunable parameter, which serves as a penalty of the original similarity measure. The optimal value is learned through supervised learning and thus is adaptive to data distribution. To evaluate the performance of our proposed algorithm, we conduct extensive experiments on eleven disparate networks of the real world. Experimental results show that AdaSim achieves better performance than state-of-the-art algorithms and is robust to different sparsities of the networks.

An effective similarity measure based on kernel spectral method for complex networks

2019 ◽  
Vol 30 (07) ◽  
pp. 1940005
Author(s):  
Longjie Li ◽  
Lu Wang ◽  
Shenshen Bai ◽  
Shiyu Fang ◽  
Jianjun Cheng ◽  
...  
Keyword(s):  
Network Analysis ◽  
Spectral Method ◽  
Similarity Measure ◽  
Link Prediction ◽  
Structural Information ◽  
Critical Role ◽  
Similarity Measures ◽  
Global Information ◽  
Kernel Matrix ◽  
Node Similarity

Node similarity measure is a special important task in complex network analysis and plays a critical role in a multitude of applications, such as link prediction, community detection, and recommender systems. In this study, we are interested in link-based similarity measures, which only concern the structural information of networks when estimating node similarity. A new algorithm is proposed by adopting the idea of kernel spectral method to quantify the similarity of nodes. When computing the kernel matrix, the proposed algorithm makes use of local structural information, but it takes advantage of global information when constructing the feature matrix. Thence, the proposed algorithm could better capture potential relationships between nodes. To show the superiority of our algorithm over others, we conduct experiments on 10 real-world networks. Experimental results demonstrate that our algorithm yields more reasonable results and better performance of accuracy than baselines.

scholarly journals Learning Signed Network Embedding via Graph Attention

2020 ◽  
Vol 34 (04) ◽  
pp. 4772-4779 ◽  
Author(s):  
Yu Li ◽  
Yuan Tian ◽  
Jiawei Zhang ◽  
Yi Chang
Keyword(s):  
Network Analysis ◽  
Real World ◽  
Link Prediction ◽  
Critical Role ◽  
Network Embedding ◽  
Convolutional Networks ◽  
Importance Coefficient ◽  
Signed Network ◽  
Low Dimensional ◽  
Negative Links

Learning the low-dimensional representations of graphs (i.e., network embedding) plays a critical role in network analysis and facilitates many downstream tasks. Recently graph convolutional networks (GCNs) have revolutionized the field of network embedding, and led to state-of-the-art performance in network analysis tasks such as link prediction and node classification. Nevertheless, most of the existing GCN-based network embedding methods are proposed for unsigned networks. However, in the real world, some of the networks are signed, where the links are annotated with different polarities, e.g., positive vs. negative. Since negative links may have different properties from the positive ones and can also significantly affect the quality of network embedding. Thus in this paper, we propose a novel network embedding framework SNEA to learn Signed Network Embedding via graph Attention. In particular, we propose a masked self-attentional layer, which leverages self-attention mechanism to estimate the importance coefficient for pair of nodes connected by different type of links during the embedding aggregation process. Then SNEA utilizes the masked self-attentional layers to aggregate more important information from neighboring nodes to generate the node embeddings based on balance theory. Experimental results demonstrate the effectiveness of the proposed framework through signed link prediction task on several real-world signed network datasets.

Link prediction based on heterogeneous degree penalization with extending neighbors and clustering coefficient

2021 ◽  
Author(s):  
Rongrong Song ◽  
Guang Ling ◽  
Qingju Fan ◽  
Ming-Feng Ge ◽  
Fang Wang
Keyword(s):  
Local Structure ◽  
Link Prediction ◽  
Similarity Index ◽  
Similarity Measures ◽  
Clustering Coefficient ◽  
The Other ◽  
Challenging Problem ◽  
Structure Information ◽  
Node Similarity ◽  
A Current

Link prediction, aiming to find missing links in a current network or to predict some possible new links in a future network, is a challenging problem in complex networks. Many existing link prediction algorithms perform the task by optimizing the node similarity measures, and then determining the possibility of the link between any pair of similar nodes. In this paper, we propose a novel node similarity index named heterogeneous degree penalization (HDP), which incorporates the quasi-local structure information of extending neighborhood of each pair of nodes to be predicted and the clustering coefficient of their common neighbors. For specific networks with different statistical properties, we can achieve a good performance of link prediction through adjusting the penalty weights. The experiment results show that, comparing with the other existing approaches, the proposed method can remarkably improve the accuracy of link prediction.

Sign in / Sign up

Export Citation Format

Share Document