Question for the support of dhg for heterogeneous hypergraph

[mgao97]

I am wondering whether dhg supports hypergraph datasets with heterogeneous graphs, which means that for each hyperedge, there are several types of entities.

[yifanfeng97]

Absolutely, a heterogeneous hyperedge will have a more powerful modeling ability. It is a good direction for DHG's future work. Can you provide more materials? Some related links like code repositories, papers, and datasets of existing heterogeneous structures?

[mgao97]

Thanks! I have no ability to offer materials of such characteristics, and looking forward to your findings!

------------------ 原始邮件 ------------------ 发件人: "iMoonLab/DeepHypergraph" @.>; 发送时间: 2022年9月19日(星期一) 晚上7:08 @.>; @.@.>; 主题: Re: [iMoonLab/DeepHypergraph] Question for the support of dhg for heterogeneous hypergraph (Issue #9)

Absolutely, a heterogeneous hyperedge will have a more powerful modeling ability. It is a good direction for DHG's future work. Can you provide more materials? Some related links like code repositories, papers, and datasets of existing heterogeneous structures?

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

[beating-1224]

There was a study on node classification task ,which proposed a graph neural network-based representation learning framework for heterogeneous hypergraphs. This work has been published in WSDM，named Heterogeneous Hypergraph Embedding for Graph Classification. It may give you some reference.