minchen00 / graph-unlearning Goto Github PK

Traceback (most recent call last):
File "/home/gfq/code/privacy/Graph-Unlearning-main/lib_gnn_model/node_classifier.py", line 203, in
graphsage.train_model()
File "/home/gfq/code/privacy/Graph-Unlearning-main/lib_gnn_model/node_classifier.py", line 80, in train_model
out = self.model(self.data.x[n_id], adjs, self.edge_weight)
File "/home/gfq/anaconda3/envs/unlearning/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/gfq/code/privacy/Graph-Unlearning-main/lib_gnn_model/gcn/gcn_net_batch.py", line 20, in forward
x = self.convs[i]((x, x_target), edge_index, edge_weight=edge_weight[e_id])
File "/home/gfq/anaconda3/envs/unlearning/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/gfq/code/privacy/Graph-Unlearning-main/lib_gnn_model/gcn/gcn_conv_batch.py", line 22, in forward
out = torch.matmul(out, self.weight) #报错拉！
File "/home/gfq/anaconda3/envs/unlearning/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'GCNConvBatch' object has no attribute 'weight'

进程已结束，退出代码为 1

If we change out = torch.matmul(out, self.weight) to out = self.lin(out) in Graph-Unlearning-main/lib_gnn_model/gcn/gcn_net_batch.py, it works, but by default citeseer training set set the accuracy is only about 40%.

Is there any further explanation about the parameters?

I have some questions when I run it, for example, "partition_method" defaults to sage_km, but under this parameter I need to load the model, and I haven't noticed where to train it.

Also, after I change "partition_method" to "random", it runs successfully. At the time of "unlearning", the following error is reported:
Traceback (most recent call last):
File "/home/gfq/code/privacy/Graph-Unlearning-main/main.py", line 54, in
main(args, args['exp'])
File "/home/gfq/code/privacy/Graph-Unlearning-main/main.py", line 42, in main
ExpUnlearning(args)
File "/home/gfq/code/privacy/Graph-Unlearning-main/exp/exp_unlearning.py", line 32, in init
self.train_target_models(run)
File "/home/gfq/code/privacy/Graph-Unlearning-main/exp/exp_unlearning.py", line 74, in train_target_models
for shard in range(self.num_shards):
AttributeError: 'ExpUnlearning' object has no attribute 'num_shards'

File "/home/gfq/code/privacy/Graph-Unlearning-main/exp/exp_attack_unlearning.py", line 166, in attack_graph_unlearning
with open(config.MODEL_PATH + self.args['dataset_name'] + "/" + self.args['target_model'] +"_unlearned_indices") as file:
FileNotFoundError: [Errno 2] No such file or directory: 'temp_data/models/citeseer/GAT_unlearned_indices'

I am experimenting under '--exp' is 'attack_unlearning', what are the parameters under which this file was created?