Timezone: »

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
Lin Lan · Pinghui Wang · Xuefeng Du · Kaikai Song · Jing Tao · Xiaohong Guan

Wed Dec 09 09:00 PM -- 11:00 PM (PST) @ Poster Session 4 #1162

We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier. The study of this problem is instructive and corresponds to many applications such as recommendations for newly formed groups with only a few users in online social networks. To cope with this problem, we propose a novel Meta Transformed Network Embedding framework (MetaTNE), which consists of three modules: (1) A \emph{structural module} provides each node a latent representation according to the graph structure. (2) A \emph{meta-learning module} captures the relationships between the graph structure and the node labels as prior knowledge in a meta-learning manner. Additionally, we introduce an \emph{embedding transformation function} that remedies the deficiency of the straightforward use of meta-learning. Inherently, the meta-learned prior knowledge can be used to facilitate the learning of few-shot novel labels. (3) An \emph{optimization module} employs a simple yet effective scheduling strategy to train the above two modules with a balance between graph structure learning and meta-learning. Experiments on four real-world datasets show that MetaTNE brings a huge improvement over the state-of-the-art methods.

Author Information

Lin Lan (Xi'an Jiaotong University)
Pinghui Wang (Xi'an Jiaotong University)
Xuefeng Du (Xi'an Jiaotong University)
Kaikai Song (Huawei Noah's Ark Lab)
Jing Tao (Xi'an Jiaotong University)
Xiaohong Guan (Xi'an Jiaotong University)