DeepHypergraph
DeepHypergraph copied to clipboard
iMoonLab
A pytorch library for graph and hypergraph computation.
在虚拟环境中安装dhg包时，在Collecting sklearn (from dhg)过程中出现error：subprocess-exited-with-error，详细情况如下： “ Collecting sklearn (from dhg) Using cached sklearn-0.0.post12.tar.gz (2.6 kB) Preparing metadata (setup.py) ... error error: subprocess-exited-with-error × python setup.py egg_info did not run successfully. │...
**根据超图节点集进行超图子图的抽取** 是否可以实现这样一个关于子图的函数，用户输入这个超图有关的节点集，就能返回包含这个节点集的超图子图。 关于超边的选择方面，一种策略是可以保留全空超边，另一种策略是只保留至少包含一个节点的超边。
### Discussed in https://github.com/iMoonLab/DeepHypergraph/discussions/23 Originally posted by **ShuaiWang97** December 5, 2022 To the community, Hope you had a great weekend. Thank you so much for building this package! I am...
Hi, Thank you for providing this great project! I'm wondering if we can generate a corresponding hypergraph dataset based on a real-world GNN graph embedding dataset?
It is a really great project! However, I met some issues in the process. Is this package able to deal with a directed hypergraph or not? Because in the hypergraph,...
您好，我想请问下。在dhg文档中，有份示例代码，是用于构造具有不同超边权重的超图卷积模型（代码附在下面）。我想问的是，这个超边特征Y是不是得先进将顶点信息传递到边后，即先调用 hg.v2e才可以拿到这个超边特征。 class HGATConv(nn.Module): def __init__( self, in_channels: int, out_channels: int, bias: bool = True, drop_rate: float = 0.5, atten_neg_slope: float = 0.2, ): super().__init__() self.atten_dropout = nn.Dropout(drop_rate) self.atten_act =...
**Describe the bug** In the paper 'UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks,' the input to the attention module of UniGAT is the vector obtained by concatenating...
你好，你们的工作让我受益匪浅，最近也在使用你们的工具进行一些超图的实验，但针对于论文《HGNN+》期刊中的adaptive fusion策略，我并没有找到相应的文档信息，代码中也并没有找到相应的例子，可能是我寻找方式不对，但俺确实是找不到，求大佬指点迷津
import torch import torch.nn as nn import torch.optim as optim from dhg import Hypergraph from dhg.data import Cooking200 from dhg.models import HGNNP from dhg.random import set_seed from dhg.experiments import HypergraphVertexClassificationTask...
@staticmethod def _e_list_from_feature_kNN(features: torch.Tensor, k: int): r"""Construct hyperedges from the feature matrix. Each hyperedge in the hypergraph is constructed by the central vertex and its :math:`k-1` neighbor vertices. Args: ``features``...
