cxw-droid

MetaApprox much higher accuracy for perturbed graph

4

Hi, Thanks for sharing the DeepRobust code. I am testing the `mettack.py` code using `test_mettack.py`. When the model is `A-Meta-Self`, the attacked graph accuracy is much higher than `Meta-Self` model....

Hi, In the readme file under `graphdata` folder, there are some strange characters as follows, ``` NOTICE: 1. All labels cannot be ¡°0¡± or ¡°1¡±, and it should be larger...

Thank you for sharing the code. I found an error when I tried to preprocess the data. > Traceback (most recent call last): File "PrepareDatasets.py", line 73, in preprocess_dataset(dataset_name, args_dict)...

Hi, There is an error when I tried to train a new model for `PGExplainer`: ` $ /bin/bash ./models/train_gnns.sh`: > AttributeError: 'GCNConv' object has no attribute '\_\_explain__' The error is...

rl-s2v implementation

1

Hi, it seems only targeted node classification attack is implemented for [`rl-s2v paper.`](https://arxiv.org/abs/1806.02371) If so, do you plan to implement its attacks on graph classifications? Thanks.

Hi, the graph embedding used in the paper is structure2vec embedding. Do you know where there is a python 3 implementation of structure2vec without using c++? I tried to replace...

multiple edges modification

2

Hi, it seems the code only modifies one edge per graph. Is there a simpler way to change the code to multiple edges modification? I have not found a parameter...

AUC results different from the paper

5

Thank you for sharing the code. The test results for dataset `BlogCatalog`, `Flickr` and `ACM` are `0.8142, 0.7944, 0.8967` respectively, significantly different from the results shown on Figure 2 of...

Hi, thank you for you code. https://github.com/PyGCL/PyGCL/blob/c2f4dc73e449d26a109dbefede287ea0fca93c4b/GCL/augmentors/functional.py#L100 May I know why you set the `F.dropout` probability to `1. - drop_prob` instead of the original `drop_prob`? I.e., why the code here...

xgraph/pgexplainer

2

Hello, when I try to run [examples/xgraph/pgexplainer.ipynb](https://github.com/divelab/DIG/tree/dig-stable/examples/xgraph/pgexplainer.ipynb), there is an error: > splitted_dataset.slices['mask'] = splitted_dataset.slices['train_mask'] TypeError: 'NoneType' object is not subscriptable I am using torch-geometric 2.1.0. Could any one please...