ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Outlier resistant unsupervised deep architectures for attributed network embedding

Bandyopadhyay, S and Lokesh, N and Vivek, SV and Murty, MN (2020) Outlier resistant unsupervised deep architectures for attributed network embedding. In: WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining, 3-7 Feb., 2020, Houston, USA, pp. 25-33.

WSDM 20.pdf - Published Version

Download (3MB) | Preview
Official URL: https://dx.doi.org/10.1145/3336191.3371788


Attributed network embedding is the task to learn a lower dimensional vector representation of the nodes of an attributed network, which can be used further for downstream network mining tasks. Nodes in a network exhibit community structure and most of the network embedding algorithms work well when the nodes, along with their attributes, adhere to the community structure of the network. But real life networks come with community outlier nodes, which deviate significantly in terms of their link structure or attribute similarities from the other nodes of the community they belong to. These outlier nodes, if not processed carefully, can even affect the embeddings of the other nodes in the network. Thus, a node embedding framework for dealing with both the link structure and attributes in the presence of outliers in an unsupervised setting is practically important. In this work, we propose a deep unsupervised autoencoders based solution which minimizes the effect of outlier nodes while generating the network embedding. We use both stochastic gradient descent and closed form updates for faster optimization of the network parameters. We further explore the role of adversarial learning for this task, and propose a second unsupervised deep model which learns by discriminating the structure and the attribute based embeddings of the network and minimizes the effect of outliers in a coupled way. Our experiments show the merit of these deep models to detect outliers and also the superiority of the generated network embeddings for different downstream mining tasks. To the best of our knowledge, these are the first unsupervised non linear approaches that reduce the effect of the outlier nodes while generating Network Embedding.

Item Type: Conference Paper
Publication: WSDM 2020 - Proceedings of the 13th International Conference on Web Search and Data Mining
Publisher: Association for Computing Machinery, Inc
Additional Information: cited By 0; Conference of 13th ACM International Conference on Web Search and Data Mining, WSDM 2020 ; Conference Date: 3 February 2020 Through 7 February 2020; Conference Code:157225
Keywords: Data mining; Embeddings; Gradient methods; Information retrieval; Learning systems; Social networking (online); Stochastic systems; Websites, Adversarial learning; Auto encoders; Community outliers; Graph mining; Network representation, Statistics
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Date Deposited: 29 Jun 2020 10:40
Last Modified: 29 Jun 2020 10:40
URI: http://eprints.iisc.ac.in/id/eprint/64704

Actions (login required)

View Item View Item