English

Generalising Recursive Neural Models by Tensor Decomposition

Machine Learning 2020-06-18 v1 Neural and Evolutionary Computing Machine Learning

Abstract

Most machine learning models for structured data encode the structural knowledge of a node by leveraging simple aggregation functions (in neural models, typically a weighted sum) of the information in the node's neighbourhood. Nevertheless, the choice of simple context aggregation functions, such as the sum, can be widely sub-optimal. In this work we introduce a general approach to model aggregation of structural context leveraging a tensor-based formulation. We show how the exponential growth in the size of the parameter space can be controlled through an approximation based on the Tucker tensor decomposition. This approximation allows limiting the parameters space size, decoupling it from its strict relation with the size of the hidden encoding space. By this means, we can effectively regulate the trade-off between expressivity of the encoding, controlled by the hidden size, computational complexity and model generalisation, influenced by parameterisation. Finally, we introduce a new Tensorial Tree-LSTM derived as an instance of our framework and we use it to experimentally assess our working hypotheses on tree classification scenarios.

Keywords

Cite

@article{arxiv.2006.10021,
  title  = {Generalising Recursive Neural Models by Tensor Decomposition},
  author = {Daniele Castellana and Davide Bacciu},
  journal= {arXiv preprint arXiv:2006.10021},
  year   = {2020}
}

Comments

Accepted at IEEE WCCI2020

R2 v1 2026-06-23T16:24:39.419Z