graph_adversarial_attack

graph_adversarial_attack copied to clipboard

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...

cxw-droid

Question about hierarchical Q-Learning

4

Hi, hanjun. Thanks a lot for your great work! I have a question about the hierarchical Q-Learning mentioned in the paper. In equation 11, there are 2M Q functions and...

matouk98

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...

cxw-droid

instruction does not work

6

When I run git clone [email protected]:Hanjun-Dai/graph_adversarial_attack --recursive It says permission denied. I need to git clone pytorch_structure2vec separately

wangxiaoyunanne

Where is "_ext"?

3

Hello! I meet a problem when running the codes: In custom_func.py, there is a code : "from _ext import my_lib", however, I can't find this pakage named "_ext", could you...

mujm

Question on the "isTerminal" function

1

The `isTerminal(self)` function is in located at `graph_adversarial_attack/code/graph_attack/rl_common.py`. > def isTerminal(self): > if self.n_steps == 2 * self.n_edges: > return True > return False When initializing, `self.n_edges` is set `1`,...

lijianwen96

Error with graph_attack and node_classification

4

I am able to successfully run the graph classification, but when I try to attack the graph, I get this error: undefined symbol: __cudaRegisterFatBinaryEnd This error occurs with each attack...

clb0063

Add some dependencies to readme, to make sure the code can run normally.

KaiyuanZh

https://github.com/Hanjun-Dai/graph_adversarial_attack/blob/57b2853d32e2412dba2c78d10b9a1659954cc49b/code/graph_attack/nstep_replay_mem.py#L54-L66 Is this hash function problematic? It seems that this function is equivalent to `key = a_t % base`.

xiaojunxu