Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification

8 Sep 2020 Yunsheng Shi Zhengjie Huang Shikun Feng Hui Zhong Wenjin Wang Yu Sun

Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification ogbn-arxiv unimp Test Accuracy 73.11 # 1
Validation Accuracy 74.5 # 1
Node Classification ogbn-products UniMP Test Accuracy 82.56 # 1
Validation Accuracy 93.08 # 1
Node Classification ogbn-proteins unimp Test Accuracy 86.42 # 1
Validation Accuracy 91.75 # 1

Methods used in the Paper


METHOD TYPE
GCN
Graph Models
Layer Normalization
Normalization
Dropout
Regularization
Dense Connections
Feedforward Networks
Scaled Dot-Product Attention
Attention Mechanisms
BPE
Subword Segmentation
Label Smoothing
Regularization
Multi-Head Attention
Attention Modules
Adam
Stochastic Optimization
Residual Connection
Skip Connections
Softmax
Output Functions
Transformer
Transformers