Suhansanu Kumar
University of Illinois at Urbana–Champaign
7 Papers
39 Citations
Suhansanu Kumar is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Snowball sampling & Computer science. The author has an hindex of 3, co-authored 7 publications.
Chat about Author
Papers
On the categorization of scientific citation profiles in computer science
TL;DR: In this article, a dynamic growth model reveals how citation networks evolve over time, pointing the way toward reformulated scientometrics, and the authors propose a new model for citation networks.
41
FITNet: Identifying Fashion Influencers on Twitter
Jinda Han,Qinglin Chen,Xilun Jin,Weikai Xu,Wanxian Yang,Suhansanu Kumar,Li Zhao,Hari Sundaram,Ranjitha Kumar +8 more
- 22 Apr 2021
TL;DR: In this article, a network of the top 10k influencers of the larger Twitter fashion graph was constructed by using a content-based classifier to identify fashion-relevant Twitter accounts.
17
Attribute-Guided Network Sampling Mechanisms
Suhansanu Kumar,Hari Sundaram +1 more
TL;DR: A task-independent, attribute aware link-trace sampler grounded in Information Theory is proposed, which tends to rapidly explore the attribute space, maximally reducing the surprise of unseen nodes and proves that content sampling is an NP-hard problem.
6
•Posted Content
Task-driven sampling of attributed networks.
Suhansanu Kumar,Hari Sundaram +1 more
TL;DR: New techniques for sampling attributed networks to support standard Data Mining tasks are introduced and several attribute-aware samplers based on Information Theoretic principles are introduced, proving that these Samplers have a bias towards capturing new content, and are equivalent to uniform sampling in the limit.
3
Centrality and Community Scoring Functions in Incomplete Networks: Their Sensitivity, Robustness, and Reliability
Soumya Sarkar,Suhansanu Kumar,Sanjukta Bhowmick,Animesh Mukherjee +3 more
- 01 Jan 2018
TL;DR: This paper focuses on two distinct types of parameters—community scoring functions and centrality measures and identifies the effect of removal of edges in terms of the sensitivity, robustness and reliability, and discusses, in detail, how the joint community-like andcentrality-like characteristic of permanence makes it an interesting metric for noisy graphs.
3