Planetoid-处理原始Cora、Pubmed、Citeseer图数据的方法-用图嵌入重温半监督学习

python test_ind.py

You can refer to test_trans.py and test_ind.py for example usages of our model.

Models

The models are implemented mainly in trans_model.py (transductive) and ind_model.py (inductive), with inheritance from base_model.py. You might refer to the source files for detailed API documentation.

Prepare the data

Transductive learning

The input to the transductive model contains:

• x, the feature vectors of the training instances,
• y, the one-hot labels of the training instances,
• graph, a dict in the format {index: [index_of_neighbor_nodes]}, where the neighbor nodes are organized as a list. The current version only supports binary graphs.

Let L be the number of training instances. The indices in graph from 0 to L - 1 must correspond to the training instances, with the same order as in x.

Inductive learning

The input to the inductive model contains:

• x, the feature vectors of the labeled training instances,
• y, the one-hot labels of the labeled training instances,
• allx, the feature vectors of both labeled and unlabeled training instances (a superset of x),
• graph, a dict in the format {index: [index_of_neighbor_nodes]}.

Let n be the number of both labeled and unlabeled training instances. These n instances should be indexed from 0 to n - 1 in graph with the same order as in allx.

Preprocessed datasets

Datasets for Citeseet, Cora, and Pubmed are available in the directory data, in a preprocessed format stored as numpy/scipy files.

The dataset for DIEL is available at http://www.cs.cmu.edu/~lbing/data/emnlp-15-diel/emnlp-15-diel.tar.gz. We also provide a much more succinct version of the dataset that only contains necessary files and some (not very well-organized) pre-processing code here at http://cs.cmu.edu/~zhiliny/data/diel_data.tar.gz.

The NELL dataset can be found here at http://www.cs.cmu.edu/~zhiliny/data/nell_data.tar.gz.

In addition to x, y, allx, and graph as described above, the preprocessed datasets also include:

• tx, the feature vectors of the test instances,
• ty, the one-hot labels of the test instances,
• test.index, the indices of test instances in graph, for the inductive setting,
• ally, the labels for instances in allx.

The indices of test instances in graph for the transductive setting are from #x to #x + #tx - 1, with the same order as in tx.

You can use cPickle.load(open(filename)) to load the numpy/scipy objects x, y, tx, ty, allx, ally, and graph. test.index is stored as a text file.

Hyper-parameter tuning

自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。

深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！

因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注：Python）

这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新**

如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注：Python）