Graph Echo State Networks
- 1 July 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 1-8
Abstract
In this paper we introduce the Graph Echo State Network (GraphESN) model, a generalization of the Echo State Network (ESN) approach to graph domains. GraphESNs allow for an efficient approach to Recursive Neural Networks (RecNNs) modeling extended to deal with cyclic/acyclic, directed/undirected, labeled graphs. The recurrent reservoir of the network computes a fixed contractive encoding function over graphs and is left untrained after initialization, while a feed-forward readout implements an adaptive linear output function. Contractivity of the state transition function implies a Markovian characterization of state dynamics and stability of the state computation in presence of cycles. Due to the use of fixed (untrained) encoding, the model represents both an extremely efficient version and a baseline for the performance of recursive models with trained connections. The performance are shown on standard benchmark tasks from Chemical domains, allowing the comparison with both Neural Network and Kernel-based approaches for graphs.Keywords
This publication has 16 references indexed in Scilit:
- Neural Network for Graphs: A Contextual Constructive ApproachIEEE Transactions on Neural Networks, 2009
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Markovian Bias of Neural-based Architectures With Feedback Connections2007
- Assignment kernels for chemical compounds2006
- Graph kernels for chemical informaticsNeural Networks, 2005
- Optimal assignment kernels for attributed molecular graphs2005
- Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless CommunicationScience, 2004
- Markovian Architectural Bias of Recurrent Neural NetworksIEEE Transactions on Neural Networks, 2004
- Recurrent Neural Networks with Small Weights Implement Definite Memory MachinesNeural Computation, 2003
- Introduction to Discrete Dynamical Systems and Chaos1999