Estimating network edge probabilities by neighborhood smoothing
Duration: 31 mins
Share this media item:
Embed this media item:
Embed this media item:
About this item
Description: |
Levina, E (University of Michigan)
Thursday 14th July 2016 - 11:30 to 12:00 |
---|
Created: | 2016-07-20 10:14 |
---|---|
Collection: | Theoretical Foundations for Statistical Network Analysis |
Publisher: | Isaac Newton Institute |
Copyright: | Levina, E |
Language: | eng (English) |
Abstract: | Co-authors: Yuan Zhang (Ohio State University), Ji Zhu (University of Michigan)
The problem of estimating probabilities of network edges from the observed adjacency matrix has important applications to predicting missing links and network denoising. It has usually been addressed by estimating the graphon, a function that determines the matrix of edge probabilities, but is ill-defined without strong assumptions on the network structure. Here we propose a novel computationally efficient method based on neighborhood smoothing to estimate the expectation of the adjacency matrix directly, without making the strong structural assumptions graphon estimation requires. The neighborhood smoothing method requires little tuning, has a competitive mean-squared error rate, and outperforms many benchmark methods on the task of link prediction in both simulated and real networks. Related Links http://arxiv.org/abs/1509.08588 - paper |
---|
Available Formats
Format | Quality | Bitrate | Size | |||
---|---|---|---|---|---|---|
MPEG-4 Video | 640x360 | 1.94 Mbits/sec | 451.62 MB | View | Download | |
WebM | 640x360 | 714.37 kbits/sec | 162.29 MB | View | Download | |
iPod Video | 480x270 | 522.35 kbits/sec | 118.60 MB | View | Download | |
MP3 | 44100 Hz | 249.8 kbits/sec | 56.78 MB | Listen | Download | |
Auto * | (Allows browser to choose a format it supports) |