Comments (4)
整图分类的难点是:把一个batch的图或超图进行打包,比如特征X和A矩阵进行拼接,然后就可以加速训练。现阶段来说可以参考这个代码 https://github.com/weihua916/powerful-gnns/blob/master/models/graphcnn.py#L111 。当然我们也在尽快集成图/超图整图分类的相关函数接口,预计在下个版本上线哦
from deephypergraph.
正如作者所说,确实在超图打包遇到了困难,感谢大佬提供的解决方案,方便问一下新版本什么时候会上线吗?我想及时关注一下。顺便想提一个建议:能否在整图分类中统计节点在分类中的贡献度,例如通过反向传播的过程中计算节点的权重,以此作节点贡献度排序。
from deephypergraph.
下个版本预计4月份上线。
反向可视化确实是一个很好的小工具,能提供很强的解释性。俺尽力实现一下,尽量在下个版本加进来^_^
from deephypergraph.
作者您好,我最近也在做超图的整图分类任务,但好像没有看到你们实现节点到整图的消息传递的功能。目前在整图分类任务上也遇到了一些困难 T^T,请问一下下个版本什么时候能够上线呢 ?
from deephypergraph.
Related Issues (20)
- Dataset: Coauthor network from DBLP HOT 9
- hypergraph.e2v_aggregation_of_group方法出错 HOT 2
- kindly need help to for several reproduction results HOT 3
- 超图的顶点度矩阵D_v HOT 11
- 超图如何采集负样本? HOT 4
- How to transform a igraph or networkx object into hypergraph? HOT 5
- About Directed Hypergraph HOT 3
- adaptive fusion和coequal fusion的文档问题 HOT 2
- How to use HGNN+ for RL
- mini-batches training for node classification on hypergraph
- Unable to install dhg using pip HOT 2
- CoauthorshipCora dataset label error HOT 1
- 请帮忙看一下画图代码draw_hypergraph()的参数无法调整如v_line_width和e_line_width,限制输入的格式错了,修改也没变化。 HOT 2
- 我针对你的超图写了个邻接矩阵的接口,想请老哥帮忙看看写的对不对?我自己也做了个些测试,输出的挺对,你介意合并不? HOT 2
- 中文文档有误
- 大型图的处理
- torch.topk 函数设置 largest=False 是为了找到最小的距离,即最近的邻居。这种方法可能比转换张量为 numpy 数组并使用 scipy.spatial.cKDTree 更有效,因为它避免了 CPU 和 GPU 之间的数据传输。 HOT 1
- 如何获取训练后节点的向量?
- e_weight=None,agg='softmax' 时Graph类v2v中x=torch.sparse.mm(P,dim=1)应该是x=torch.sparse.softmax(P,dim=1)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from deephypergraph.