Structure-Sensitive Graph Dictionary Embedding for Graph Classification
This work addresses graph classification, a key task in fields like bioinformatics and social network analysis, by introducing a novel adaptation mechanism, though it appears incremental as it builds upon existing dictionary-based approaches.
The authors tackled graph classification by proposing a Structure-Sensitive Graph Dictionary Embedding (SS-GDE) framework that adapts a base graph dictionary to each input graph, resulting in improved performance over state-of-the-art methods on multiple datasets.
Graph structure expression plays a vital role in distinguishing various graphs. In this work, we propose a Structure-Sensitive Graph Dictionary Embedding (SS-GDE) framework to transform input graphs into the embedding space of a graph dictionary for the graph classification task. Instead of a plain use of a base graph dictionary, we propose the variational graph dictionary adaptation (VGDA) to generate a personalized dictionary (named adapted graph dictionary) for catering to each input graph. In particular, for the adaptation, the Bernoulli sampling is introduced to adjust substructures of base graph keys according to each input, which increases the expression capacity of the 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 further deduces to variational inference of the adapted graph dictionary. We perform our SS-GDE on multiple datasets of graph classification, and the experimental results demonstrate the effectiveness and superiority over the state-of-the-art methods.