Compositionality-Aware Graph2Seq Learning. (arXiv:2201.12178v1 [cs.LG])

Web: http://arxiv.org/abs/2201.12178

Graphs are a highly expressive data structure, but it is often difficult for
humans to find patterns from a complex graph. Hence, generating
human-interpretable sequences from graphs have gained interest, called
graph2seq learning. It is expected that the compositionality in a graph can be
associated to the compositionality in the output sequence in many graph2seq
tasks. Therefore, applying compositionality-aware GNN architecture would
improve the model performance. In this study, we adopt the multi-level
attention pooling (MLAP) architecture, that can aggregate …

arxiv learning