DHGNN
DHGNN copied to clipboard
iMoonLab
DHGNN source code for IJCAI19 paper: "Dynamic Hypergraph Neural Networks"
Bumps [nbconvert](https://github.com/jupyter/nbconvert) from 5.3.1 to 6.3.0. Release notes Sourced from nbconvert's releases. 5.5.0 Documentation Release This tag is used to provide a working documentation build for RTD. Commits cefe0bf Release...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [mistune](https://github.com/lepture/mistune) from 0.8.3 to 2.0.3. Release notes Sourced from mistune's releases. Version 2.0.2 Fix escape_url via lepture/mistune#295 Version 2.0.1 Fix XSS for image link syntax. Version 2.0.0 First release...
Bumps [distributed](https://github.com/dask/distributed) from 1.21.8 to 2021.10.0. Commits 63ebaea bump version to 2021.10.0 1670cf8 Ensure resumed flight tasks are still fetched (#5426) cdc68cc AMM high level documentation (#5456) 33d83bc Provide stack...
Bumps [lxml](https://github.com/lxml/lxml) from 4.2.1 to 4.9.1. Changelog Sourced from lxml's changelog. 4.9.1 (2022-07-01) Bugs fixed A crash was resolved when using iterwalk() (or canonicalize()) after parsing certain incorrect input. Note...
Bumps [numpy](https://github.com/numpy/numpy) from 1.14.3 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
Bumps [notebook](http://jupyter.org) from 5.5.0 to 6.4.12. [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a...
There are so many problems with the requirements.txt file, which doesn't install packages in google colab. Some package's version don't match. Could you please update this for colab, or can...
请问G表示什么含义呢？我在论文中没有找到相关含义
作者你好，阅读论文后发现你们关于动态构建超图网络的想法非常酷，也很受启发。特别是论文中谈到的关于微博推文情感分析任务，我觉得用超图网络来做情感分析任务很有意思。 我想问一下关于使用动态超图网络来做情感分析任务的一些细节问题，因为我没有从代码里找到关于情感分析任务相关的代码或者微博推文数据处理的代码。 1. 不同于cora数据，情感分析任务中的数据本身不存在图结构（把每一篇推文看作一个节点的话，节点之间是没有关联的）。所以我很好奇，针对情感分析任务，输入数据是不存在结构（edge_dict节点仅自相关），还是说对数据做了预处理，节点之间构建了关联并将其作为先验知识输入模型。如果做了预处理，是怎么样做的？ 2. 关于训练数据，不知道我理解有没有偏差，我没有在代码中看到batch_size的设置，模型似乎是针对所有训练数据进行建模的。我看到论文里介绍的推文数据量是5550条，如果数据量较大，例如有20万条推文，该方法是否可行？有哪些应对方法？（我看到代码中有矩阵H和G计算，节点数量到十万量级那么矩阵计算代价会非常恐怖）
