Code about graphcl

[yyou1996]

Hi, @wangzeyu135798,

The code should automatically download the dataset at the first run if you download the correct dependencies. Please feel free to drop questions if it still not works.

[wangzeyu135798]

你好：       感谢你的回复！       在运行你的github代码的时候，在semisupervised_TU/pre-training/tu_dataset.py line 50 报错，错误为不存在.pt文件。       我想问下代码在自动下载数据的时候包括相关的.pt文件吗？我看到你的这个项目在github网页上提到了gfn-master，对于gfn-master这套代码，我也遇到了相关的问题。 

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Shen-Lab/GraphCL" <[email protected]&gt;; 发送时间:&nbsp;2020年10月30日(星期五) 晚上9:36 收件人:&nbsp;"Shen-Lab/GraphCL"<[email protected]&gt;; 抄送:&nbsp;"天津工业大学王泽宇"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [Shen-Lab/GraphCL] Code (#1) Hi, @wangzeyu135798, The code should automatically download the dataset at the first run if you download the correct dependencies. Please feel free to drop questions if it still not work. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[yyou1996]

包括的。他会自动下载数据，然后预处理成.pt文件。需要torch-geometric版本之类的正确才行。

[yyou1996]

I make an update to provide the conda environment file that might help you collect the required dependencies. Please see https://github.com/Shen-Lab/GraphCL/tree/master/semisupervised_TU#option-2.

Any other questions feel free to drop here. Thanks.

[wangzeyu135798]

Hi: &nbsp;&nbsp; After reading you data, I have two questions. &nbsp;&nbsp; First, is one positive pair is the same graph data instance augmented in two aspects? &nbsp;&nbsp; Second, when calculating the loss, line res_gcn.py line 233, loss = pos_sim / (sim_matrix.sum(dim=1)) - pos_sim - self_sim, while in paper equation(3) the last&nbsp; two components(pos_sim and self_dim) are lost, why? &nbsp;&nbsp; I hope your reply. &nbsp;&nbsp; Thanks. &nbsp; &nbsp; &nbsp; &nbsp;

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Shen-Lab/GraphCL" <[email protected]&gt;; 发送时间:&nbsp;2020年11月5日(星期四) 晚上10:59 收件人:&nbsp;"Shen-Lab/GraphCL"<[email protected]&gt;; 抄送:&nbsp;"天津工业大学王泽宇"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [Shen-Lab/GraphCL] Code (#1) Hi @wangzeyu135798, I make an update to provide the conda environment file that might help you collect the required dependencies. Please see https://github.com/Shen-Lab/GraphCL/tree/master/semisupervised_TU#option-2. Any other questions feel free to drop here. Thanks. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[wangzeyu135798]

Hi: &nbsp;&nbsp; When I run the finetuning step, there is a code error. &nbsp;&nbsp; In semisupervised_TU/finetuning/train_eval.py line 181,&nbsp; &nbsp;&nbsp; for _, idx in skf_semi.split(torch.zeros(idx_train.size()[0]), dataset[idx_trian].data.y) &nbsp;&nbsp; ValueError: Found input variables with inconsistent numbers of samples: [3699, 4110] &nbsp;&nbsp; How to solve it? &nbsp;&nbsp; Thanks.

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Shen-Lab/GraphCL" <[email protected]&gt;; 发送时间:&nbsp;2020年11月5日(星期四) 晚上10:59 收件人:&nbsp;"Shen-Lab/GraphCL"<[email protected]&gt;; 抄送:&nbsp;"天津工业大学王泽宇"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [Shen-Lab/GraphCL] Code (#1) Hi @wangzeyu135798, I make an update to provide the conda environment file that might help you collect the required dependencies. Please see https://github.com/Shen-Lab/GraphCL/tree/master/semisupervised_TU#option-2. Any other questions feel free to drop here. Thanks. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[wangzeyu135798]

你好： &nbsp; &nbsp; &nbsp; 还有一个问题。在semisupervised-TU/fine-tuning/train_eval.py 里面，调用train函数的时候是在进行有监督训练，那么此时的model不也应该被保存吗？在代码中没有看到调用train函数时模型被save。

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Shen-Lab/GraphCL" <[email protected]&gt;; 发送时间:&nbsp;2020年11月5日(星期四) 晚上10:59 收件人:&nbsp;"Shen-Lab/GraphCL"<[email protected]&gt;; 抄送:&nbsp;"天津工业大学王泽宇"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [Shen-Lab/GraphCL] Code (#1) Hi @wangzeyu135798, I make an update to provide the conda environment file that might help you collect the required dependencies. Please see https://github.com/Shen-Lab/GraphCL/tree/master/semisupervised_TU#option-2. Any other questions feel free to drop here. Thanks. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[yyou1996]

First, is one positive pair is the same graph data instance augmented in two aspects?: Yes.

Second, when calculating the loss, line res_gcn.py line 233, loss = pos_sim / (sim_matrix.sum(dim=1)) - pos_sim - self_sim, while in paper equation(3) the last  two components(pos_sim and self_dim) are lost, why? Thanks for pointing it out. The denominator in formulation should be corrected as sum_{k=1, k!=i}^N xxx.

ValueError: Found input variables with inconsistent numbers of samples: [3699, 4110] Would you mind sharing your environment.yml file that I can double-check? Thanks.

还有一个问题。在semisupervised-TU/fine-tuning/train_eval.py 里面，调用train函数的时候是在进行有监督训练，那么此时的model不也应该被保存吗？在代码中没有看到调用train函数时模型被save。 In finetuning I only saved the results before since the overall results are 10- or 100-fold evaluation with 5 runs. Of course, you can make small modification in code to save the models.

Hope my answers can help you.

[wangzeyu135798]

你好： &nbsp; &nbsp; &nbsp;我现在在看你的这篇文章When Does Self-Supervision Help Graph Convolutional Networks? 在看到Graph partition的时候，对应代码里用到了metis的一个分割图的函数metis.part_graph, 对于metis这个包，我直接pip install metis，安装0.2a4这个版本，运行后报错RuntimeError: Could not locate METIS dll. Please set the METIS_DLL environment variable to its full path.我一直没有找到解决方案。我现在的环境是windows，请问你当时是怎么安装的这个包？

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Shen-Lab/GraphCL" <[email protected]&gt;; 发送时间:&nbsp;2020年11月10日(星期二) 凌晨5:38 收件人:&nbsp;"Shen-Lab/GraphCL"<[email protected]&gt;; 抄送:&nbsp;"天津工业大学王泽宇"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [Shen-Lab/GraphCL] Code (#1) Thanks @wangzeyu135798, First, is one positive pair is the same graph data instance augmented in two aspects?: Yes. Second, when calculating the loss, line res_gcn.py line 233, loss = pos_sim / (sim_matrix.sum(dim=1)) - pos_sim - self_sim, while in paper equation(3) the last&nbsp; two components(pos_sim and self_dim) are lost, why? Thanks for pointing it out. The denominator in formulation should be corrected as sum_{k=1, k!=i}^N xxx. ValueError: Found input variables with inconsistent numbers of samples: [3699, 4110] Would you mind sharing your environment.yml file that I can double-check? Thanks. 还有一个问题。在semisupervised-TU/fine-tuning/train_eval.py 里面，调用train函数的时候是在进行有监督训练，那么此时的model不也应该被保存吗？在代码中没有看到调用train函数时模型被save。 In finetuning I only saved the results before since the overall results are 10- or 100-fold evaluation with 5 runs. Of course, you can make small modification in code to save the models. Hope my answers can help you. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[yyou1996]

Please follow the dependencies part https://github.com/Shen-Lab/SS-GCNs#dependencies that pip install only provide your the API between python and METIS, but you also need to install METIS such that python can call METIS.

In https://github.com/Shen-Lab/SS-GCNs#dependencies for Linux thus we need to run sudo apt-get install libmetis-dev.

[wangzeyu135798]

Hi： &nbsp; &nbsp;Under SS-GCN/cluster_labels, there are three .npy files. I want to learn how to make these npy files?

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "Shen-Lab/GraphCL" <[email protected]&gt;; 发送时间:&nbsp;2020年11月12日(星期四) 晚上11:22 收件人:&nbsp;"Shen-Lab/GraphCL"<[email protected]&gt;; 抄送:&nbsp;"天津工业大学王泽宇"<[email protected]&gt;;"Mention"<[email protected]&gt;; 主题:&nbsp;Re: [Shen-Lab/GraphCL] Code (#1) Hi @wangzeyu135798, Please follow the dependencies part https://github.com/Shen-Lab/SS-GCNs#dependencies that pip install only provide your the API between python and METIS, but you also need to install METIS such that python can call METIS. In https://github.com/Shen-Lab/SS-GCNs#dependencies for Linux thus we need to run sudo apt-get install libmetis-dev. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[yyou1996]

Please see the bottom of this README.md https://github.com/Shen-Lab/SS-GCNs/tree/master/SS-GCNs#training--evaluation.