Diagnosis: Make Bipartite Graph crashes

[jonnie]

Hello I found a new nut for you to crack
I have this example network here and it's annotated with diagnostic information and I want to create a bipartite graph out of it!
Unfortunately, GeNIe crashes. But it doesn't crash when I remove the yellow node (by deletion or marginalization doesn't matter)...
Can you tell me what's the reason?
Greetings Johannes

[shooltz[BayesFusion]]

The crash was due to determinism in the network. You can download modified binaries using the link I've provided previously.

[jonnie]

Yeah, works! Awesome bugfix time
Now I'm sorry, but making a bipartite graph still crashes when I want to convert the whole network... The crash looks different this time. I'll send you the problematic network via PM.
The crash is immediate so I guess GeNIe is not running out of computer resources, it's something wrong with the network structure or CPTs again...

[shooltz[BayesFusion]]

The crash is immediate so I guess GeNIe is not running out of computer resources

It does, actually. On my machine the failure happens when adding 18th parent to one of nodes in the bipartite graph. The size of CPT needs to increase to 134217728 entries (approx. 1GB of contiguous memory). The allocation fails and std::bad_alloc is not caught, bringing GeNIe down.

[jonnie]

Haha, I guess that network is simply not meant for bipartition!
Well I've looked on my task manager and I didn't see any memory spike before GeNIe went down, so I figured that can't be the reason... Maybe it would be possible if GeNIe could generate a noisyMAX bipartite graph, but then again, this would probably approximate the JPD too much...
Thank you a lot!