v0.9.4 release

[yifanfeng97]

We are releasing the v0.9.4 version now! In v0.9.4, we add 6 hypergraph datasets and fix some known bugs.

New Datasets:

• DBLP-4k @yifanfeng97
• IMDB4k @yifanfeng97
• Recipe100k @yifanfeng97
• Recipe200k @yifanfeng97
• Yelp3k @yifanfeng97
• Tencent2k @yifanfeng97

Fix bugs:

• fix last layer bn bugs @yifanfeng97
• fix device error of graph,di_graph,bi_graph,hypergraph laplacian computing @yifanfeng97

New features:

• add custom hypergraph generator @yifanfeng97

---

This discussion was created from the release v0.9.4 release.

[ddl-donglin]

Why are you so niubility? Orz

[yifanfeng97]

You niubility, too. Orz

[Liker79]

DaLao，we've recently been working on a project that doesn't involve multimodal data, where we want to use a single object as a vertex, connected by some relationship, which acts as a superedge, and then classify the entire hypergraph. But I see only vertex classification in the documentation, and I wonder if your framework can implement full graph classification. Or can I add a full connection layer after all vertexes output to achieve full graph output?
大佬，我们最近在做相关的课题，不涉及多模态的数据，想以单一的客体做节点，通过某些关系连接起来，这些关系作为超边，然后针对整张超图做分类。但是我看到文档中仅有节点分类的内容，不知道您的框架能否实现全图分类。或者我能否在所有节点输出之后加一个全连接层实现全图输出？