A Bayesian Framework for Estimating Properties of Network Diffusions thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

A Bayesian Framework for Estimating Properties of Network Diffusions

Published on Oct 07, 20141842 Views

The analysis of network connections, diffusion processes and cascades requires evaluating properties of the diffusion network. Properties of interest often involve variables that are not explicitly ob

Related categories

Chapter list

A Bayesian Framework for Estimating Properties of Network Diffusions00:00
Network Diffusion00:14
Problems in Network Diffusion Analysis01:21
Example Property: Leaders of tribes (LoT)02:44
Evaluating Joint Properties: Challenges04:22
Expectations of Network Diffusion Properties06:37
Bayesian Network Diffusion Analysis08:45
Computational Tractability10:10
Interesting Network Diffusion Properties12:59
Approximate Evaluation of Not-nice Properties14:26
Experiments: Algorithms14:49
Synthetic Data Experiments14:56
Synthetic Data Experiments: Weak LoT Reconstruction14:58
Synthetic Data Experiments: One-to-one Properties15:22
Real Data Experiments15:39
Scaling Experiments16:08
Closing Thoughts16:24