The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space. Existing graph representation learning methods can be classified into two categories: generative models that learn the underlying connectivity distribution in the graph, and discriminative models that predict the probability of edge existence between a pair of vertices. In this paper, we propose GraphGAN, an innovative graph representation learning framework unifying above two classes of methods, in which the generative model and discriminative model play a game-theoretical minimax game.

Task | Dataset | Model | Metric name | Metric value | Global rank | Compare |
---|---|---|---|---|---|---|

Node Classification | BlogCatalog | GraphGAN | Accuracy | 23.20% | # 1 | |

Node Classification | BlogCatalog | GraphGAN | Macro-F1 | 0.221 | # 1 | |

Node Classification | Wikipedia | GraphGAN | Accuracy | 21.30% | # 1 | |

Node Classification | Wikipedia | GraphGAN | Macro-F1 | 0.194 | # 1 |