Is there any more explanation about the procedures?

[guanfaqian]

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'

[guanfaqian]

pickle.dump(lpa_deltas, open(config.ANALYSIS_PATH + "partition/baseblpa" + self.args['dataset_name'], 'wb')) FileNotFoundError: [Errno 2] No such file or directory: 'temp_data/analysis_data/partition/base_blpa_citeseer'

Does this need to be created on its own or is there a file to run first?

[MinChen00]

Hi, thanks for the information.

I have fixed the issue in exp_unlearning.py. num_shards is a parameter passed from the parameter_parser.py file, all the self.num_shards should be self.args['num_shards'].

For the second question, yes, some directories need to be created to save the partition data and trained models. The details can be found in config.py file.

[guanfaqian]

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'

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