SSSNET: Semi-Supervised Signed Network Clustering

He, Yixuan; Reinert, Gesine; Wang, Songchao; Cucuringu, Mihai

doi:10.1137/1.9781611977172.28

Cited by 12 publications

(20 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first present experiments on synthetic data generated by signed stochastic block model (Cucuringu et al, 2019;He et al, 2022a) with different levels of imbalance. We simulate two clusters with intra-cluster edge probability of 0.02 having positive signs and inter-cluster probability of 0.01 having negative signs.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Signed Graph Neural Networks: A Frequency Perspective

Singh¹,

Chen²

2022

Preprint

View full text Add to dashboard Cite

Graph convolutional networks (GCNs) and its variants are designed for unsigned graphs containing only positive links. Many existing GCNs have been derived from the spectral domain analysis of signals lying over (unsigned) graphs and in each convolution layer they perform low-pass filtering of the input features followed by a learnable linear transformation. Their extension to signed graphs with positive as well as negative links imposes multiple issues including computational irregularities and ambiguous frequency interpretation, making the design of computationally efficient low pass filters challenging. In this paper, we address these issues via spectral analysis of signed graphs and propose two different signed graph neural networks, one keeps only low-frequency information and one also retains highfrequency information. We further introduce magnetic signed Laplacian and use its eigendecomposition for spectral analysis of directed signed graphs. We test our methods for node classification and link sign prediction tasks on signed graphs and achieve state-of-the-art performances.

show abstract

Section: Resultsmentioning

confidence: 99%

“…SDGNN (Huang et al, 2021) is a recent work applicable to signed directed graphs based on balance and status theory. SSSNET (He et al, 2022a) is another GNN based work with a focus on clustering of signed graphs. For balanced graphs, the eigenvectors of the signed Laplacian follow certain properties as analyzed in (Dittrich & Matz, 2020).…”

Section: Introductionmentioning

confidence: 99%

Signed Graph Neural Networks: A Frequency Perspective

Singh¹,

Chen²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In a similar vein, SNEA [11] proposes a signed graph neural network for link sign prediction based on a novel objective function. In a different line of work, [12] proposes SSSNET, a GNN not based on balance theory designed for semi-supervised node clustering in signed (and possibly directed) graphs.…”

Section: Related Workmentioning

confidence: 99%

“…The goal of this paper is to introduce a novel Laplacian and an associated spectral GNN for signed directed graphs. While spatial GNNs exist, such as SDGNN [3], SiGAT [10], SNEA [11], and SSSNET [12] proposed for signed (and possibly directed) networks, this is one of the first works to propose a spectral GNN for such networks.…”

Section: Introductionmentioning

confidence: 99%

“…In addition to testing MSGNN on established data sets, we also devise a novel synthetic model which we call the Signed Directed Stochastic Block Model (SDSBM), which generalizes both the (undirected) Signed Stochastic Block Model from [12] and the (unsigned) Directed Stochastic Block Model from [5]. Analogous to these previous models, our SDSBM can be defined by a meta-graph structure and additional parameters describing density and noise levels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian

He¹,

Permultter²,

Reinert³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Signed and directed networks are ubiquitous in real-world applications. However, there has been relatively little work proposing spectral graph neural networks (GNNs) for such networks. Here we introduce a signed directed Laplacian matrix, which we call the magnetic signed Laplacian, as a natural generalization of both the signed Laplacian on signed graphs and the magnetic Laplacian on directed graphs. We then use this matrix to construct a novel efficient spectral GNN architecture and conduct extensive experiments on both node clustering and link prediction tasks. In these experiments, we consider tasks related to signed information, tasks related to directional information, and tasks related to both signed and directional information. We demonstrate that our proposed spectral GNN is effective for incorporating both signed and directional information, and attains leading performance on a wide range of data sets. Additionally, we provide a novel synthetic network model, which we refer to as the signed directed stochastic block model, and a number of novel real-world data sets based on lead-lag relationships in financial time series.Preprint. Preliminary work.

show abstract

Neural discovery of balance-aware polarized communities

Gullo,

Mandaglio,

Tagarelli

2024

Mach Learn

View full text Add to dashboard Cite

Signed graphs are a model to depict friendly (positive) or antagonistic (negative) interactions (edges) among users (nodes). 2-Polarized-Communities (2pc) is a well-established combinatorial-optimization problem whose goal is to find two polarized communities from a signed graph, i.e., two subsets of nodes (disjoint, but not necessarily covering the entire node set) which exhibit a high number of both intra-community positive edges and negative inter-community edges. The state of the art in 2pc suffers from the limitations that (i) existing methods rely on a single (optimal) solution to a continuous relaxation of the problem in order to produce the ultimate discrete solution via rounding, and (ii) 2pc objective function comes with no control on size balance among communities. In this paper, we provide advances to the 2pc problem by addressing both these limitations, with a twofold contribution. First, we devise a novel neural approach that allows for soundly and elegantly explore a variety of suboptimal solutions to the relaxed 2pc problem, so as to pick the one that leads to the best discrete solution after rounding. Second, we introduce a generalization of 2pc objective function – termed $$\gamma $$ γ -polarity – which fosters size balance among communities, and we incorporate it into the proposed machine-learning framework. Extensive experiments attest high accuracy of our approach, its superiority over the state of the art, and capability of function $$\gamma $$ γ -polarity to discover high-quality size-balanced communities.

show abstract

SSSNET: Semi-Supervised Signed Network Clustering

Cited by 12 publications

References 39 publications

Signed Graph Neural Networks: A Frequency Perspective

Signed Graph Neural Networks: A Frequency Perspective

MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian

Neural discovery of balance-aware polarized communities

Contact Info

Product

Resources

About