xnhp
commented
2 years ago Hi Olga,
it's possible. What the simplest approach is depends on the format your data is in.
The most general way is to implement a custom "loader" function (an example is in the "contrib" subdirectory). A loader is a function that returns a list of DeepSNAP graphs, if I remember correctly. Then, in your experiment's config file, you specify to use that loader.
Best Regards, Ben
On Tue, Nov 2, 2021, 10:37 Olga Lazareva @.***> wrote:
Hi! I'm a little confused if it's actually possible to use my own dataset in a PyG format or not. load_pyg function kind of suggests that the name of a dataset can only be one of the fixed ones (CiteSeer, PPI, Cora, etc) while the readme states that a PyG upload should be possible: "GraphGym currently accepts a list of NetworkX graphs or PyG datasets.". If PyG format for the custom data is not possible then I guess it must be networkx. Is there any example how those graphs should look like? In particular, I'm interested in graph classification, if that matters.
Olga
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/snap-stanford/GraphGym/issues/31, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAB2LED6EYSLCMOTNP26LTTUJ6WPJANCNFSM5HF7TCPA .
Laolga
Hi! I'm a little confused if it's actually possible to use my own dataset in a PyG format or not. load_pyg function kind of suggests that the name of a dataset can only be one of the fixed ones (CiteSeer, PPI, Cora, etc) while the readme states that a PyG upload should be possible: "GraphGym currently accepts a list of NetworkX graphs or PyG datasets.". If PyG format for the custom data is not possible then I guess it must be networkx. Is there any example how those graphs should look like? In particular, I'm interested in graph classification, if that matters.
Olga