benedekrozemberczki / datasets Goto Github PK

你好,请问有标签的数据集可以作为deepwalk的输入么?怎样才能转化为.mat文件呢?

Hi,
I had a question relating to the features.json file. It would be great if you could tell me what the features represent?

Thanks

Could you provide an example of how to download the datasets?

The zip file for Deezer Europe Dataset has 2 CSV files that only contain git-lfs pointers. How to download the dataset from git-lfs pointers you placed in CSVs?

Hi,
First of all, I would like to genuinely thank you for your incredibly clear and detailed guidance. To be honest, I am very new to the field of GNN and have just started delving into it a few weeks ago, so I still have a lot of questions about how they operate.

In the data description section, node features are described as being extracted based on the location, starred repositories, employer, and email address. Therefore, I think features should be text or something similar. However, in the musae_git_features.json file, the features are numerical vectors. I also looked into various other datasets, and node features have a similar form. I genuinely do not understand how to process these features from raw data into numerical vectors that can serve as input for GNNs.

Thank you so much!

how to generate embeddings using your library if my input is in grapson(json) or graphml(xml) format?

I have a question about the LastfmAsia and DeezerEurope datasets of your CIKM 2020 paper, which I found on SNAP. These datasets are provided with node features which are “extracted based on the artists liked by the users”. Does this mean that each number in the vector associated to each node corresponds to the id of an artist that the user node liked? Or is the vector a more abstract embedding? I am referring to the file lastfm_asia_features.json and deezer_europe_features.json.

Thanks in advance!

The target files in twitch social network contain the following columns id,days,mature,views,partner,new_id. Could you please provide some information regarding these values, and also, can you please point which column is used for the node classification task ?

Hello,
Thank you for your work!

For the features.json file in the twitch dataset, is there a reference for what the feature indices in the values list specifically represent? For e.g: it's mentioned the features are extracted from games played. Do some of the values in the list represent ids of the games played by that user? Is there a way to get information on what each value corresponds to?

Hi,

The features in git_web_ml/git_feature.json are not of same length. Should the shorter ones be padded with 0s to the end? Or is there a feature matrix of shape (node_num, feature_num) or a sparse mat with node_id, feature_id and value?

Thank you!

So I am trying to download the Facebook Large dataset. But the zip file has 2 CSV files that only contain git-lfs pointers:

Any idea how to retrieve the dataset from these git-lfs pointers?

Thanks!

The zip file for facebook-large Dataset has 2 CSV files that only contain git-lfs pointers. How to download the dataset from git-lfs pointers you placed in CSVs?