Revisiting Semi-Supervised Learning with Graph Embeddings

We present a semi-supervised learning framework based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification Citeseer Planetoid-I Accuracy 64.7% # 44
Document Classification Cora Planetoid* Accuracy 75.7% # 6
Node Classification Cora Planetoid-I Accuracy 75.7% # 49
Node Classification NELL Planetoid* Accuracy 61.9% # 4
Node Classification Pubmed Planetoid-I Accuracy 77.2% # 41
Node Classification USA Air-Traffic Planetoid* Accuracy 64.7 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet