Spectral Embedding of Signed Networks

Zheng, Quan; Skillicorn, David B.

doi:10.1137/1.9781611974010.7

Cited by 43 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 ) is analogous to minimizing the Rayleigh quotient of SNS graph Laplacian in signed network spectral embedding [17]. This reflects that our designed pairwise constraints are indeed able to capture and preserve the extended structural balance property of the signed networks.…”

Section: B Pairwise Constraintsmentioning

confidence: 70%

“…The top-d eigenvectors of L SNS are selected as the node vector representations. 3) BNS [17]: It is a spectral embedding algorithm with the BNS Laplacian matrix defined as L BNS =D −1 (D + −A). The top-d eigenvectors of L BNS are selected as the node vector representations.…”

Section: Baseline Algorithmsmentioning

confidence: 99%

“…For other baselines in link sign prediction, we used the same dimensionality of node vector representation as in our DNE-SBP model, i.e., d = 64. In addition, note that the spectral embedding algorithms, i.e., SL, SNS, and BNS, assume that the top-k eigenvectors encode the corresponding k-way clustering structure [7], [17]. Thus, for the community detection task, the dimensionality of the node vector representations learned by these spectral embedding algorithms were set as equal to the number of clusters in the given network, i.e., d = k.…”

Section: Baseline Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Deep Network Embedding for Graph Representation Learning in Signed Networks

Shen

Chung

2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Network embedding has attracted an increasing attention over the past few years. As an effective approach to solve graph mining problems, network embedding aims to learn a low-dimensional feature vector representation for each node of a given network. The vast majority of existing network embedding algorithms, however, are only designed for unsigned networks, and the signed networks containing both positive and negative links, have pretty distinct properties from the unsigned counterpart. In this paper, we propose a deep network embedding model to learn the low-dimensional node vector representations with structural balance preservation for the signed networks. The model employs a semisupervised stacked auto-encoder to reconstruct the adjacency connections of a given signed network. As the adjacency connections are overwhelmingly positive in the real-world signed networks, we impose a larger penalty to make the auto-encoder focus more on reconstructing the scarce negative links than the abundant positive links. In addition, to preserve the structural balance property of signed networks, we design the pairwise constraints to make the positively connected nodes much closer than the negatively connected nodes in the embedding space. Based on the network representations learned by the proposed model, we conduct link sign prediction and community detection in signed networks. Extensive experimental results in real-world datasets demonstrate the superiority of the proposed model over the state-of-the-art network embedding algorithms for graph representation learning in signed networks.

show abstract

Section: B Pairwise Constraintsmentioning

confidence: 70%

Section: Baseline Algorithmsmentioning

confidence: 99%

Section: Baseline Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Network Embedding for Graph Representation Learning in Signed Networks

Shen

Chung

2020

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…4. Balanced Normalized Signed Laplacian (BNS) model: Zheng and Skillicorn (2015) proposed two spectral approaches for modeling and analyzing the signed graphs based on the random walk normalized Laplacian matrix. 5.…”

Section: Baselinesmentioning

confidence: 99%

Attending Over Triads for Learning Signed Network Embedding

Sodhani

Tang

2019

Front. Big Data

View full text Add to dashboard Cite

Network embedding, which aims at learning distributed representations for nodes in networks, is a critical task with wide downstream applications. Most existing studies focus on networks with a single type of edges, whereas in many cases, the edges of networks can be derived from two opposite relationships, yielding signed networks. This paper studies network embedding for the signed network, and a novel approach called TEA is proposed. Similar to existing methods, TEA (Triad+Edge+Attention) learns node representations by predicting the sign of each edge in the network. However, many existing methods only consider the local structural information (i.e., the representations of nodes in an edge) for prediction, which can be biased especially for sparse networks. By contrast, TEA seeks to leverage the high-order structures by drawing inspirations from the Structural Balance Theory. More specifically, for an edge linking two nodes, TEA predicts the edge sign by considering the triangles connecting the two nodes as features. Meanwhile, an attention mechanism is proposed, which assigns different weights to the different triangles before aggregating their predictions for more precise results. We conduct experiments on several real-world signed networks, and the results prove the effectiveness of TEA over many strong baseline approaches.

show abstract

“…On the other hand, the complexity of sentiment generation and the sparsity of sentiment links make it hard for algorithms to achieve desirable performance. Recently, several studies [12,14,31,35] propose methods to solve the problem of predicting signed links. However, they rely heavily on manually designed features and cannot work well in real-world scenarios.…”

mentioning

confidence: 99%

Shine

Wang

Zhang

Hou

et al. 2018

Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining

261

View full text Add to dashboard Cite

In online social networks people often express attitudes towards others, which forms massive sentiment links among users. Predicting the sign of sentiment links is a fundamental task in many areas such as personal advertising and public opinion analysis. Previous works mainly focus on textual sentiment classification, however, text information can only disclose the "tip of the iceberg" about users' true opinions, of which the most are unobserved but implied by other sources of information such as social relation and users' profile. To address this problem, in this paper we investigate how to predict possibly existing sentiment links in the presence of heterogeneous information. First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users' sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method. Then we propose a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users' latent representations from heterogeneous networks and predict the sign of unobserved sentiment links. SHINE utilizes multiple deep autoencoders to map each user into a low-dimension feature space while preserving the network structure. We demonstrate the superiority of SHINE over state-of-the-art baselines on link prediction and node recommendation in two real-world datasets. The experimental results also prove the efficacy of SHINE in cold start scenario.

show abstract

Spectral Embedding of Signed Networks

Cited by 43 publications

References 19 publications

Deep Network Embedding for Graph Representation Learning in Signed Networks

Deep Network Embedding for Graph Representation Learning in Signed Networks

Attending Over Triads for Learning Signed Network Embedding

Shine

Contact Info

Product

Resources

About