Question: Similiar to Receptive Field

[chengq220]

Hello. I'm fairly new to ML, AI, and Pytorch so I'm having some difficulty trying to visualize which individual nodes in the original graph affect the convoluted node in the new graph after convolution. So for example, I want to know which nodes in the original graph G affect the first node in the G' (graph after convolution) and which affects the second nodes, etc.. Thank you so much for your assistance.

[rusty1s]

Mh, this is a tricky question to answer. In the end, all neighbors have a positive or negative contribution to the central nodes, and they are only ignored in case the weights at the sample points multiplied by the neighbor's features will be close to zero across all feature dimensions, i.e., all "nearly zero rows" here.

[chengq220]

Understood. Additionally, are there any possible ways for a central node to be affected by non-neighbors nodes?

[rusty1s]

No, this is not possible.

[chengq220]

Thank you