Rethinking Kernel Methods for Node Representation Learning on Graphs

NeurIPS 2019 Yu TianLong ZhaoXi PengDimitris N. Metaxas

Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification. However, the use of kernel methods for node classification, which is a related problem to graph representation learning, is still ill-posed and the state-of-the-art methods are heavily based on heuristics... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Link Prediction Citeseer Node Feature Agg + Similarity Metric AUC 90.9% # 5
AP 91.8% # 4
Link Prediction Cora Node Feature Agg + Similarity Metric AUC 93.1% # 4
AP 93.2% # 3
Link Prediction Pubmed Node Feature Agg + Similarity Metric AUC 94.5% # 4
AP 94.2% # 4