MUSE: Multi-faceted Attention for Signed Network Embedding

Yan, Dengcheng; Zhang, Youwen; Li, Wei; Zhang, Yiwen

doi:10.48550/arxiv.2104.14449

Cited by 2 publications

(2 citation statements)

References 28 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering interactions between positive and negative edges jointly is another main inspiration for our method, but SSSNET is not driven by such social balance theory principles. Many other GNNs [26,25,34,11,32,55] are also based on social balance theory, usually applied to data with strong positive class imbalance. Numerous other signed network embedding methods [9,10,50,28,53] also do not explore the node clustering problem.…”

Section: Related Work 21 Network Embedding and Clusteringmentioning

confidence: 99%

“…Most competitive state-of-the-art methods generating node embeddings for signed networks focus on link sign prediction [28,11,53,32,9,55,17], and those that pertain to node clustering are not GNN methods [49,53,31,12,15]. Here, we introduce a graph neural network (GNN) framework, called SSSNET, with a Signed Mixed-Path Aggregation (SIMPA) scheme, to obtain node embeddings for signed clustering.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SSSNET: Semi-Supervised Signed Network Clustering

He¹,

Reinert²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Node embeddings are a powerful tool in the analysis of networks; yet, their full potential for the important task of node clustering has not been fully exploited. In particular, most state-of-the-art methods generating node embeddings of signed networks focus on link sign prediction, and those that pertain to node clustering are usually not graph neural network (GNN) methods. Here, we introduce a novel probabilistic balanced normalized cut loss for training nodes in a GNN framework for semi-supervised signed network clustering, called SSSNET. The method is end-to-end in combining embedding generation and clustering without an intermediate step; it has node clustering as main focus, with an emphasis on polarization effects arising in networks. The main novelty of our approach is a new take on the role of social balance theory for signed network embeddings. The standard heuristic for justifying the criteria for the embeddings hinges on the assumption that an "enemy's enemy is a friend". Here, instead, a neutral stance is assumed on whether or not the enemy of an enemy is a friend. Experimental results on various data sets, including a synthetic signed stochastic block model, a polarized version of it, and real-world data at different scales, demonstrate that SSSNET can achieve comparable or better results than state-of-the-art spectral clustering methods, for a wide range of noise and sparsity levels. SSSNET complements existing methods through the possibility of including exogenous information, in the form of node-level features or labels.

show abstract