Goto

Collaborating Authors

Community Detection in Networks: The Leader-Follower Algorithm

arXiv.org Machine Learning

Traditional spectral clustering methods cannot naturally learn the number of communities in a network and often fail to detect smaller community structure in dense networks because they are based upon external community connectivity properties such as graph cuts. We propose an algorithm for detecting community structure in networks called the leader-follower algorithm which is based upon the natural internal structure expected of communities in social networks. The algorithm uses the notion of network centrality in a novel manner to differentiate leaders (nodes which connect different communities) from loyal followers (nodes which only have neighbors within a single community). Using this approach, it is able to naturally learn the communities from the network structure and does not require the number of communities as an input, in contrast to other common methods such as spectral clustering. We prove that it will detect all of the communities exactly for any network possessing communities with the natural internal structure expected in social networks. More importantly, we demonstrate the effectiveness of the leader-follower algorithm in the context of various real networks ranging from social networks such as Facebook to biological networks such as an fMRI based human brain network. We find that the leader-follower algorithm finds the relevant community structure in these networks without knowing the number of communities beforehand. Also, because the leader-follower algorithm detects communities using their internal structure, we find that it can resolve a finer community structure in dense networks than common spectral clustering methods based on external community structure.


ICRA 2020 launches with plenary panel 'COVID-19: How Roboticists Can Help'

Robohub

ICRA is the largest robotics meeting in the world and is the flagship conference of the IEEE Robotics & Automation Society. It is thus our honor and pleasure to welcome you to this edition, although the current exceptional circumstances did not allow us to organize it in Paris as planned with the glimpse and splendor that our wonderful robotics community deserves. Now, for sure, Virtual ICRA 2020, the first online ICRA, will be one of the most memorable ICRA editions ever! Our first Plenary is a hot topic panel on COVID-19 Pandemic & Robotics, moderated by Ken Goldberg and chaired by Wolfram Burgard. Join us for the virtual conference taking place May 31 to August 31 with sessions available both live and on demand.


hackers.ai Applied AI Conference

#artificialintelligence

To learn more, request information about our AI Global ambassadors program. More information about the speakers and the final agenda will be announced shortly. Coffee and lunch will be provided during the conference. The full speakers line up will be announced shortly.


hackers.ai Applied AI Conference

#artificialintelligence

To learn more, request information about our AI Global ambassadors program. Coffee and lunch will be provided during the conference. The selected companies will have the unique opportunity to promote their product/service during the conference, have free access to the event, and meet with industry leaders. Be recognized as a leader in Silicon Valley and address an audience of top startups, industry leaders, corporations, and investors. Scout innovation, hire new talent, create strategic partnerships, and learn about the latest technologies and industry trends.


IBM InterConnect: Blockchain in enterprise ecosystems - Blockchain Unleashed: IBM Blockchain Blog

#artificialintelligence

In the words of Jerry Cuomo, Vice President of Blockchain Technologies at IBM, "Blockchain is a team sport. Your business thrives because it's part of an ecosystem of interconnected businesses." He said this during the blockchain keynote at IBM InterConnect 2017, and over the course of the conference I've come to agree with him. Blockchain is all about enterprise ecosystems, for it is in these ecosystems that blockchain can provide the most value. Additionally, I've seen how important it is to have partners and be part of a community when developing blockchain solutions.