Skip to content

Baseline复现结果和文章不一致 #442

Description

@KevinGao7

您好!
我在运行代码:experiment(dataset="ppi", model="deepwalk", dw="network_embedding_dw", mw="network_embedding_mw", training_percents=[0.5]) 后,输出的 micro-F1=0.6416。然而,文章:“CogDL: A Comprehensive Library for Graph Deep Learning” Table 5 中的结果:micro-F1=0.2074。
这两个数据对应不上,想问下是哪里出问题了?是否是因为不能采用默认参数设置?怎么才能具体复现出Table 5中的结果呢?感谢!

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions