Learning Graph Weighted Models on Pictures
Abstract
Graph Weighted Models (GWMs) have recently been proposed as a natural generalization of weighted automata over strings and trees to arbitrary families of labeled graphs (and hypergraphs). A GWM generically associates a labeled graph with a tensor network and computes a value by successive contractions directed by its edges. In this paper, we consider the problem of learning GWMs defined over the graph family of pictures (or 2-dimensional words). As a proof of concept, we consider regression and classification tasks over the simple Bars & Stripes and Shifting Bits picture languages and provide an experimental study investigating whether these languages can be learned in the form of a GWM from positive and negative examples using gradient-based methods. Our results suggest that this is indeed possible and that investigating the use of gradient-based methods to learn picture series and functions computed by GWMs over other families of graphs could be a fruitful direction.
Cite
@article{arxiv.1806.08297,
title = {Learning Graph Weighted Models on Pictures},
author = {Philip Amortila and Guillaume Rabusseau},
journal= {arXiv preprint arXiv:1806.08297},
year = {2018}
}
Comments
International Conference on Grammatical Inference 2018 (v2: camera-ready)