Multiplex visibility graphs to investigate recurrent neural networks dynamics
This work addresses the challenge of hyperparameter tuning in RNNs for researchers and practitioners, offering a principled alternative to trial-and-error methods, though it is incremental as it builds on existing graph-based techniques.
The authors tackled the problem of tuning hyperparameters in recurrent neural networks (RNNs) by proposing a graph-based framework to interpret internal dynamics, resulting in an unsupervised method that improved prediction error and memory capacity, with experiments on benchmarks and real-world datasets.
A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning of such hyperparameters may be difficult and, typically, based on a trial-and-error approach. In this work, we adopt a graph-based framework to interpret and characterize the internal RNN dynamics. Through this insight, we are able to design a principled unsupervised method to derive configurations with maximized performances, in terms of prediction error and memory capacity. In particular, we propose to model time series of neurons activations with the recently introduced horizontal visibility graphs, whose topological properties reflect important dynamical features of the underlying dynamic system. Successively, each graph becomes a layer of a larger structure, called multiplex. We show that topological properties of such a multiplex reflect important features of RNN dynamics and are used to guide the tuning procedure. To validate the proposed method, we consider a class of RNNs called echo state networks. We perform experiments and discuss results on several benchmarks and real-world dataset of call data records.