Some Questions about Your Implemention

[ghost]

Hi Jiaxuan:
Thank you for your source code. It helps me a lot. Recently I'm trying to replicate this paper by tensorflow. However, I encounter some questions when I'm trying to understand your source code.

1. As detailed in Page 4 "Concretely, the l-th P-GNN layer first samples k random anchor-sets S_i." and algorithm， should I resample anchor-sets at every layer of P-GNN? In your source code, (mode.py line 90 - line 100), anchor-sets are resampled at every epoch.

2. In model.py, you say:"only pick closest node for message passing". Combining it with your code to undersatnd, I think that you only use feature of the closest node in a anchor set. It's contradictory with this statement "We find that using simple MEAN aggregation function provides good result".

I look forward to your reply.

[chao1224]

@fanninnypeom I got the same questions, as posted in #13. Another similar issue can be found in #11 .

Below is my guess:

	Paper	Implementation
1	resample every epoch and every layer	resample every epoch, but fixed for each layer
2	$AGG_M$ is MEAN	$AGG_M$ is MAX (Another issue here is what if there exist multiple nodes with the same closest distance? Now the solution is to simply take the last node in the anchor set.)

Please correct me if I'm wrong here.

[Deepak-Work]

@fanninnypeom @chao1224 Were you able to figure out Q2. "$AGG_M$ is MEAN"?
I have the same question and am wondering if changing the implementation to incorporate MEAN aggregator improves the performance.

Any help is appreciated.