How to understand the NN part, e.g., qnet.cpp

[tianshangaga]

I find it is not easy to understand how does the nn works, e.g., the func 'QNet::SetupGraphInput()' and ' QNet::BuildNet()', so can you give more detailed instructions about the code? thanks a lot!

[Hanjun-Dai]

Hi,

In general this code is building the symbolic computation graph first, and then run the forward/backward. This is similar to tensorflow's logic.

Regarding the two functions you are talking about:
SetupGraphInput is setting up the input, similar to setting up 'feed_dict' in tensorflow.
BuildNet is just building that static symbolic computation graph.

Let me know if you have further questions.

[Amirinezhad]

Hi, thanks for sharing code!
Do you have any documents or tutorials that explains how to use factor_graph.h library to build a custom factor graph network?

Thanks

[Hanjun-Dai]

Hi,

There was a (possibly out-dated) document: https://www.cc.gatech.edu/~hdai8/graphnn/html/annotated.html

Basically you add new operators to the computation graph through the 'af' function:
https://github.com/Hanjun-Dai/graphnn/blob/bdf51e66231d51bc2b9a560b2be255bc642d4a03/include/nn/factor_graph.h#L334

like af(computation_graph, {list of inputs}, other arguments).

But since I'm not maintaining the code base further, I would suggest to use pytorch or tensorflow for developing new models.

[Amirinezhad]

Thanks for your answer!

Sorry I have another question. In your paper, you have explained that we can use two seprate net, first for embedding that iterates (for example) 4 times, second for finding Q value-function. But in this code I can't see this structure and there is one net. Did you merge them? How?

Thanks.

[Hanjun-Dai]

It is trained jointly. For example, in MVC, up to this line was for embedding the graph, and after that we feed the embedding into another mlp to calculate the Q function.