Generalised Structural CNNs (SCNNs) for time series data with arbitrary
graph topology
release_wdg36qgdcvedbk76xeorhjhaci
by
Thomas Teh, Chaiyawan Auepanwiriyakul, John Alexander Harston, A. Aldo
Faisal
2018
Abstract
Deep Learning methods, specifically convolutional neural networks (CNNs),
have seen a lot of success in the domain of image-based data, where the data
offers a clearly structured topology in the regular lattice of pixels. This
4-neighbourhood topological simplicity makes the application of convolutional
masks straightforward for time series data, such as video applications, but
many high-dimensional time series data are not organised in regular lattices,
and instead values may have adjacency relationships with non-trivial
topologies, such as small-world networks or trees. In our application case,
human kinematics, it is currently unclear how to generalise convolutional
kernels in a principled manner. Therefore we define and implement here a
framework for general graph-structured CNNs for time series analysis. Our
algorithm automatically builds convolutional layers using the specified
adjacency matrix of the data dimensions and convolutional masks that scale with
the hop distance. In the limit of a lattice-topology our method produces the
well-known image convolutional masks. We test our method first on synthetic
data of arbitrarily-connected graphs and human hand motion capture data, where
the hand is represented by a tree capturing the mechanical dependencies of the
joints. We are able to demonstrate, amongst other things, that inclusion of the
graph structure of the data dimensions improves model prediction significantly,
when compared against a benchmark CNN model with only time convolution layers.
In text/plain
format
Archived Files and Locations
application/pdf 3.9 MB
file_x43mbck5cvdfxbjepvyyvunxda
|
arxiv.org (repository) web.archive.org (webarchive) |
1803.05419v1
access all versions, variants, and formats of this works (eg, pre-prints)