Structure-Sensitive Graph Dictionary Embedding for Graph Classification

Guangbu Liu, Tong Zhang, Zhen Cui, Wenting Zhao, Xudong Wang, Jian Yang

Keywords: graph classification, variational inference, attention, mutual information

Abstract:

Graph structure expression plays an important role in distinguishing various graphs. In this work, we propose a Structure-Sensitive Graph Dictionary Embedding (SS-GDE) framework to transform input graph into the space of graph dictionary for the graph classification task. Instead of a naive use of base graph dictionary, we propose variational graph dictionary adaptation (GDA) to generate a personalized dictionary (named adapted graph dictionary) for catering each input graph. In particular for the adaptation, the Bernoulli sampling is introduced to adjust substructures of base graph keys, which increases the expression capacity of base dictionary tremendously.
To make cross-graph measurement sensitive as well as stable, multi-sensitivity Wasserstein encoding is proposed to produce the embeddings by designing multi-scale attention on optimal transport. To optimize the framework, we introduce mutual information as the objective, which just deduces to variational inference of adapted graph dictionary. We perform our SS-GDE on multiple datasets of graph classification, and the experimental results demonstrate the effectiveness and the superiority over the state-of-the-art methods.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning