# Heterogeneous-Deep-Graph-Infomax **Repository Path**: marvin_jia/Heterogeneous-Deep-Graph-Infomax ## Basic Information - **Project Name**: Heterogeneous-Deep-Graph-Infomax - **Description**: No description available - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-08-25 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # Heterogeneous-Deep-Graph-Infomax Parameter Setting: # HDGI-A:
Node-level dimension: 16
Attention head: 4
Semantic-level attention vector: 8
learning rate: 0.02
# HDGI-C:
Node-level dimension: 64
Semantic-level attention vector: 8
learning rate: 0.02
# GAT:
Node-level dimension: 16
Attention head: 4
learning rate: 0.005
Drop out ratio: 0.6
# GCN:
Hidden-unit dimension: 64
learning rate: 0.01
Drop out ratio: 0.5
# RGCN:
Hidden-unit dimension: 16
learning rate: 0.01
Drop out ratio: 0
# Metapath2Vec:
Embedding dimension: 100
learning rate: 0.01
negative-samples: 5
Window: 1
# HAN:
Node-level dimension: 16
Attention head: 4
Semantic-level dimension: 8
learning rate: 0.005
Node-level Drop out ratio: 0.6
Semantic-level Drop out ratio: 0.6
# Deepwalk:
Number of walks per node: 10
Dimensions of word embeddings: 128
Length of random walk: 30
Window size for skipgram: 5
# DGI:
Hidden-unit dimension: 64
learning rate: 0.001
Drop out ratio: 0