Network structural perturbation against interlayer link prediction

Tang, Rui; Jiang, Shuyu; Chen, Xingshu; Wang, Wenxian; Wang, Wei

doi:10.1016/j.knosys.2022.109095

Cited by 6 publications

(2 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…; for GAT (Veličković et al 2018), a uv represents attention coefficients; for GraphSAGE (Hamilton, Ying, and Leskovec 2017), a uv = 1 |Nu| when using a mean aggregator. Tang et al argued that intralayer links connected with small degree nodes have the most significant impact on capturing interlayer features (Tang et al 2022). This observation might be explained from a resource allocation perspective (Zhou, Lü, and Zhang 2009).…”

Section: Cross-network Embeddingmentioning

confidence: 99%

Link Prediction in Multilayer Networks via Cross-Network Embedding

Ren,

Ding,

et al. 2024

AAAI

View full text Add to dashboard Cite

Link prediction is a fundamental task in network analysis, with the objective of predicting missing or potential links. While existing studies have mainly concentrated on single networks, it is worth noting that numerous real-world networks exhibit interconnectedness. For example, individuals often register on various social media platforms to access diverse services, such as chatting, tweeting, blogging, and rating movies. These platforms share a subset of users and are termed multilayer networks. The interlayer links in such networks hold valuable information that provides more comprehensive insights into the network structure. To effectively exploit this complementary information and enhance link prediction in the target network, we propose a novel cross-network embedding method. This method aims to represent different networks in a shared latent space, preserving proximity within single networks as well as consistency across multilayer networks. Specifically, nodes can aggregate messages from aligned nodes in other layers. Extensive experiments conducted on real-world datasets demonstrate the superior performance of our proposed method for link prediction in multilayer networks.

show abstract

Section: Cross-network Embeddingmentioning

confidence: 99%

Link Prediction in Multilayer Networks via Cross-Network Embedding

Ren,

Ding,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Improving the effect of user alignment by reducing the semantic gap can be broken down into three aspects: (1) Accurate and comprehensive representation of user characteristics. Due to the heterogeneity between different social networks, computing user similarity based on user features and network topologies is commonly influenced by noise [9,10]. Existing methods of this kind are too biased to determine whether two users of two different social networks are the same real user by simply analyzing the users' attributes, such as age and gender.…”

Section: Introductionmentioning

confidence: 99%

A Semantic-Enhancement-Based Social Network User-Alignment Algorithm

Huang

Zhao

Zhang

et al. 2023

Entropy

View full text Add to dashboard Cite

User alignment can associate multiple social network accounts of the same user. It has important research implications. However, the same user has various behaviors and friends across different social networks. This will affect the accuracy of user alignment. In this paper, we aim to improve the accuracy of user alignment by reducing the semantic gap between the same user in different social networks. Therefore, we propose a semantically enhanced social network user alignment algorithm (SENUA). The algorithm performs user alignment based on user attributes, user-generated contents (UGCs), and user check-ins. The interference of local semantic noise can be reduced by mining the user’s semantic features for these three factors. In addition, we improve the algorithm’s adaptability to noise by multi-view graph-data augmentation. Too much similarity of non-aligned users can have a large negative impact on the user-alignment effect. Therefore, we optimize the embedding vectors based on multi-headed graph attention networks and multi-view contrastive learning. This can enhance the similar semantic features of the aligned users. Experimental results show that SENUA has an average improvement of 6.27% over the baseline method at hit-precision30. This shows that semantic enhancement can effectively improve user alignment.

show abstract

Multi-constraints in deep graph convolutional networks with initial residual

Chen

2022

Appl Intell

View full text Add to dashboard Cite

Network structural perturbation against interlayer link prediction

Cited by 6 publications

References 60 publications

Link Prediction in Multilayer Networks via Cross-Network Embedding

Link Prediction in Multilayer Networks via Cross-Network Embedding

A Semantic-Enhancement-Based Social Network User-Alignment Algorithm

Multi-constraints in deep graph convolutional networks with initial residual

Contact Info

Product

Resources

About