Revisiting Semi-Supervised Learning with Graph Embeddings

29 Mar 2016  ·  Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov ·

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. We develop both transductive and inductive variants of our method. In the transductive variant of our method, the class labels are determined by both the learned embeddings and input feature vectors, while in the inductive variant, the embeddings are defined as a parametric function of the feature vectors, so predictions can be made on instances not seen during training. On a large and diverse set of benchmark tasks, including text classification, distantly supervised entity extraction, and entity classification, we show improved performance over many of the existing models.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Citeseer Planetoid-I Accuracy 64.7% # 60
Document Classification Cora Planetoid* Accuracy 75.7% # 6
Node Classification Cora Planetoid-I Accuracy 75.7% # 65
Node Classification NELL Planetoid* Accuracy 61.9% # 4
Node Classification Pubmed Planetoid* Accuracy 77.2% # 55
Node Classification USA Air-Traffic Planetoid* Accuracy 64.7 # 1


No methods listed for this paper. Add relevant methods here