Publications

A Spectral Representation of Networks: The Path of Subgraphs

Published in KDD (Acceptance Rate 15%), 2022

We propose representing networks with a 3D path in the spectral embedding space, to capture the spectral information of a network and its subgraphs.

Recommended citation: Shengmin Jin, Hao Tian, Jiayu Li, and Reza Zafarani. "A Spectral Representation of Networks: The Path of Subgraphs." In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 698-708. 2022. http://shengminjin.github.io/files/ThePathOfSubgraphs-KDD2022.pdf

The Spectral Zoo of Networks: Embedding and Visualizing Networks with Spectral Moments

Published in KDD (Acceptance Rate 17%), 2020

We build a spectral zoo of networks by representing graphs using the spectral moments of the random walk transition matrix P=AD^-1. Now graphs are just like animals in the zoo!

Recommended citation: Shengmin Jin, and Reza Zafarani. "The Spectral Zoo of Networks: Embedding and Visualizing Networks with Spectral Moments." Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020. http://shengminjin.github.io/files/SpectralZooNetworks-KDD2020.pdf

Graph-based Identification and Authentication: A Stochastic Kronecker Approach

Published in TKDE, 2020

We study the identification and authentication problems in the graph settings. We demonstrate the method can be used for biometrics, authenticating users based on their touch data on phones and tablets.

Recommended citation: Shengmin Jin, Vir Phoha and Reza Zafarani. "Graph-based Identification and Authentication: A Stochastic Kronecker Approach." IEEE Transactions on Knowledge and Data Engineering. 2020. http://shengminjin.github.io/files/GraphIdentificationTKDE.pdf

Sentiment Paradoxes in Social Networks: Why Your Friends Are More Positive Than You?

Published in ICWSM, 2020

We identified five sentiment paradoxes at different network levels.

Recommended citation: Zhou, Xinyi, Shengmin Jin, and Reza Zafarani. "Sentiment Paradoxes in Social Networks: Why Your Friends Are More Positive Than You?."In Proceedings of the International AAAI Conference on Web and Social Media, vol. 14, pp. 798-807. 2020. http://shengminjin.github.io/files/SentimentParadox.pdf

Noise-Enhanced Community Detection.

Published in Hypertext (Best paper nominated), 2020

We show and prove that you can take any community detection method, add limited noise to the network before running it, and get better communities.

Recommended citation: Abdolazimi, Reyhaneh, Shengmin Jin, and Reza Zafarani. "Noise-Enhanced Community Detection." Proceedings of the 31st ACM Conference on Hypertext and Social Media. 2020. http://shengminjin.github.io/files/htfp274-abdolazimiA.pdf

SGCN: A Graph Sparsifier Based on Graph Convolutional Networks.

Published in PAKDD, 2020

A neural network graph sparsifier that sparsifies a graph by pruning some edges.

Recommended citation: Li, Jiayu, Tianyun Zhang, Hao Tian, Shengmin Jin, Makan Fardad, and Reza Zafarani. "SGCN: A Graph Sparsifier Based on Graph Convolutional Networks." Advances in Knowledge Discovery and Data Mining 12084: 275. http://shengminjin.github.io/files/SGCNAGraphSparsifier.pdf

A Probabilistic Cascading Failure Model for Dynamic Operating Conditions.

Published in IEEE ACCESS, 2020

A cascading failure model that can quantify the impact of failed grid components on other components.

Recommended citation: Ma, Rui, Shengmin Jin, Sara Eftekharnejad, Reza Zafarani, and Wolf Peter Jean Philippe. "A Probabilistic Cascading Failure Model for Dynamic Operating Conditions." IEEE Access 8 (2020): 61741-61753. http://shengminjin.github.io/files/CascadingFailureModel.pdf

WebShapes: Network Visualization with 3D Shapes.

Published in WSDM , 2020

A web platform: WebShapes that enables researchers to visualize network data as customized 3D shapes.

Recommended citation: Shengmin Jin, Richard Wituszynski, Max Caiello-Gingold, and Reza Zafarani. "WebShapes: Network Visualization with 3D Shapes." Proceedings of the 13th International Conference on Web Search and Data Mining. 2020. http://shengminjin.github.io/files/WebShapes.pdf

Network Identification and Authentication.

Published in ICDM (Acceptance Rate 18.5%), 2019

Given an anonymized sampled graph, we can tell where it is sampled from, e.g., from Facebook, Twitter, or a fake graph.

Recommended citation: Shengmin Jin, Vir Phoha and Reza Zafarani. "Network Identification and Authentication" 2019 IEEE International Conference on Data Mining (ICDM). IEEE, 2019. http://shengminjin.github.io/files/NetworkIdentification.pdf

Representing Networks with 3D Shapes.

Published in ICDM (Acceptance Rate 8.86%), 2018

A method to represent any network with a 3D shape. Shapes capture various network properties: isomorphic graphs = same shapes, different graphs (random graphs, dense graphs, etc.) have different shapes.

Recommended citation: Shengmin Jin and Reza Zafarani. "Representing Networks with 3D Shapes." 2018 IEEE International Conference on Data Mining (ICDM). IEEE, 2018. https://shengminjin.github.io/files/NetworkShapes.pdf

Sentiment Prediction in Social Networks.

Published in ICDMW, 2018

An attempt to predict sentiments from network structure.

Recommended citation: Shengmin Jin and Reza Zafarani. "Sentiment Prediction in Social Networks." 2018 IEEE International Conference on Data Mining Workshops (ICDMW). IEEE, 2018. http://shengminjin.github.io/files/SentimentPrediction.pdf

Emotions in social networks: Distributions, patterns, and models.

Published in CIKM (Acceptance Rate 21%), 2017

Find how emotions vary across users, how they evolve, and how they are connected to social ties+the dual of structural balance (signed nodes instead of edges).

Recommended citation: Shengmin Jin and Reza Zafarani. "Emotions in social networks: Distributions, patterns, and models." Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM). ACM, 2017. http://shengminjin.github.io/files/EmotionsDPM.pdf