Spectral Analysis of Signed Graphs for Clustering, Prediction and Visualization

By J´erˆome Kunegis, Stephan Schmidt, Andreas Lommatzsch, Jürgen Lerner, Ernesto William De Luca, Sahin Albayrak. 2010

452 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiliang Tang
2. Charu C. Aggarwal
3. X. Shen
4. Fu-lai Chung
5. Xing Xie
6. Hongwei Wang
7. Fuzheng Zhang
8. Minyi Guo

In Computer Vision and Pattern Recognition

1. Charu C. Aggarwal
2. Jiliang Tang
3. Huan Liu
4. Dacheng Tao
5. Suhang Wang
6. Tyler Derr
7. Xing Xie
8. Chen Gong

In Statistical and Nonlinear Physics

1. X. Shen
2. Fu-lai Chung
3. Jiliang Tang
4. Charu C. Aggarwal
5. Yi Chang
6. Huan Liu
7. Yao Ma
8. Tyler Derr

Citations in the corpus

• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “Our problem of predicting positive and negative sentiment links connects to a large body of work on signed social networks, including trust propagation [9], spectral analysis [13], and social media mining [22].”
• Spectral Embedding of Signed Networks (2015, methodology): “We compare these new embedding techniques with a previously suggested spectral method for signed graphs [9] and show their performance on real-world datasets from Epinions and Slashdot, as well as a small dataset, the Gahuku-Gama alliance network of tribes in New Guinea.”
• A Survey of Signed Network Mining in Social Media (2015, methodology): “Then we classify and review tasks of signed network mining with representative algorithms.”
• Signed Network Embedding in Social Media (2017, background): “Another work in [21] extends spectral analysis for signed network.”
• On the consensus and bipartite consensus in high-order multi-agent dynamical systems with antagonistic interactions (2014, background): “The Laplacian matrix associated with the adjacency matrix A is defined as in [1, 13, 17], namely: L := C − A, (2) where C is the (diagonal) connectivity matrix, whose diagonal entries are the sums of the absolute values of the corresponding row entries of A, namely [C]ii = ∑”
• Recommender Systems (2016, unknown): “Other signed network techniques for collaborative filtering are discussed in [324, 325].”
• Consensus Problems on Networks With Antagonistic Interactions (2013, methodology): “The definition used in this paper for a Laplacian in the case of signed is , where in the connectivity matrix the weights are in absolute value, see [24], [31].”
• Signed Laplacian Embedding for Supervised Dimension Reduction (2014, background): “By constructing the binary signed graph and employing the signed graph Laplacian, SLE utilizes the label information and preserves the global data locality of examples simultaneously.”
• Deep Network Embedding for Graph Representation Learning in Signed Networks (2019, methodology): “” Existing signed network embedding algorithms mostly employ the spectral techniques [7], [17]–[19] to embed the original network into a low-dimensional space spanned by”
• Signed Graph Convolutional Networks (2018, methodology): “• Signed Spectral Embedding (SSE) [12]: A spectral clustering algorithm based on the proposed signed version of the Laplacian matrix.”
• Computing global structural balance in large-scale signed social networks (2011, background): “An alternative approach is taken in [18], where spectral properties of the L aplacian are investigated.”
• Clustering and Community Detection in Directed Networks: A Survey (2013, background): “[153, 154]) are trying to capture the notion of positive and negative interactions among the nodes of a network.”
• SNE: Signed Network Embedding (2017, background): “This is because a negative edge pushes away the two connected nodes in the vector space whereas a positive edge pulls them together [14].”