The paper introduces two new aggregation functions to encode structural knowledge from tree-structured data. They leverage the Canonical and Tensor-Train decompositions to yield expressive context aggregation while limiting the number of model parameters. Finally, we define two novel neural recursive models for trees leveraging such aggregation functions, and we test them on two tree classification tasks, showing the advantage of proposed models when tree outdegree increases.
Tensor decompositions in recursive neural networks for tree-structured data / Castellana D.; Bacciu D.. - ELETTRONICO. - (2020), pp. 451-456. (Intervento presentato al convegno 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2020 tenutosi a bel nel 2020).
Tensor decompositions in recursive neural networks for tree-structured data
Castellana D.
;
2020
Abstract
The paper introduces two new aggregation functions to encode structural knowledge from tree-structured data. They leverage the Canonical and Tensor-Train decompositions to yield expressive context aggregation while limiting the number of model parameters. Finally, we define two novel neural recursive models for trees leveraging such aggregation functions, and we test them on two tree classification tasks, showing the advantage of proposed models when tree outdegree increases.
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
