140 likes | 253 Views
Network Completion and Survey Sampling. Steve Hanneke and Eric P. Xing Machine Learning Department Carnegie Mellon University. The Task. I know the vertices, but what does the network look like?. Infer what the rest of the network looks like. Send out some random surveys.
E N D
Network Completion and Survey Sampling Steve Hanneke and Eric P. Xing Machine Learning Department Carnegie Mellon University
The Task I know the vertices, but what does the network look like? Infer what the rest of the network looks like. Send out some random surveys Survey:“Who are you linked to?” Want a bound on number of pairs with incorrect predictions.
Outline • Notation • A Tight Bound • Relaxations of the bound • An Example
A Tight Bound • The max in FT might be computationally hard (open problem) • Difficult to intuitively understand the behavior • So we’d like to relax the bound
Conclusions • In theory, can confidently learn a network topology from survey samples • Need a fairly strong learning bias • Future: Extensions to Snowball Sampling?