Pyramidal Reservoir Graph Neural Network

• URL: http://arxiv.org/abs/2104.04710v1
• Date: Sat, 10 Apr 2021 08:34:09 GMT
• Title: Pyramidal Reservoir Graph Neural Network
• Authors: Filippo Maria Bianchi, Claudio Gallicchio, Alessio Micheli
• Abstract summary: We propose a deep Graph Neural Network (GNN) model that alternates two types of layers. We show how graph pooling can reduce the computational complexity of the model. Our proposed approach to the design of RC-based GNNs offers an advantageous and principled trade-off between accuracy and complexity.
• Score: 18.632681846787246
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a deep Graph Neural Network (GNN) model that alternates two types of layers. The first type is inspired by Reservoir Computing (RC) and generates new vertex features by iterating a non-linear map until it converges to a fixed point. The second type of layer implements graph pooling operations, that gradually reduce the support graph and the vertex features, and further improve the computational efficiency of the RC-based GNN. The architecture is, therefore, pyramidal. In the last layer, the features of the remaining vertices are combined into a single vector, which represents the graph embedding. Through a mathematical derivation introduced in this paper, we show formally how graph pooling can reduce the computational complexity of the model and speed-up the convergence of the dynamical updates of the vertex features. Our proposed approach to the design of RC-based GNNs offers an advantageous and principled trade-off between accuracy and complexity, which we extensively demonstrate in experiments on a large set of graph datasets.

Related papers

• Addressing Heterophily in Node Classification with Graph Echo State Networks [11.52174067809364]
  We address the challenges of heterophilic graphs with Graph Echo State Network (GESN) for node classification. GESN is a reservoir computing model for graphs, where node embeddings are computed by an untrained message-passing function. Our experiments show that reservoir models are able to achieve better or comparable accuracy with respect to most fully trained deep models.
  arXiv  Detail & Related papers  (2023-05-14T19:42:31Z)
• Graphon Pooling for Reducing Dimensionality of Signals and Convolutional Operators on Graphs [131.53471236405628]
  We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0, 1]2 in the graphon space. We prove that those low dimensional representations constitute a convergent sequence of graphs and graph signals. We observe that graphon pooling performs significantly better than other approaches proposed in the literature when dimensionality reduction ratios between layers are large.
  arXiv  Detail & Related papers  (2022-12-15T22:11:34Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• GraphSVX: Shapley Value Explanations for Graph Neural Networks [81.83769974301995]
  Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data. In this paper, we propose a unified framework satisfied by most existing GNN explainers. We introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs.
  arXiv  Detail & Related papers  (2021-04-18T10:40:37Z)
• Accurate Learning of Graph Representations with Graph Multiset Pooling [45.72542969364438]
  We propose a Graph Multiset Transformer (GMT) that captures the interaction between nodes according to their structural dependencies. Our experimental results show that GMT significantly outperforms state-of-the-art graph pooling methods on graph classification benchmarks.
  arXiv  Detail & Related papers  (2021-02-23T07:45:58Z)
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning [31.42901131602713]
  We propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies. The proposed MathNet outperforms various existing GNN models, especially on big data sets.
  arXiv  Detail & Related papers  (2020-07-22T05:00:59Z)
• Second-Order Pooling for Graph Neural Networks [62.13156203025818]
  We propose to use second-order pooling as graph pooling, which naturally solves the above challenges. We show that direct use of second-order pooling with graph neural networks leads to practical problems. We propose two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second-order pooling.
  arXiv  Detail & Related papers  (2020-07-20T20:52:36Z)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)
• Optimal Transport Graph Neural Networks [31.191844909335963]
  Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation. We introduce OT-GNN, a model that computes graph embeddings using parametric prototypes.
  arXiv  Detail & Related papers  (2020-06-08T14:57:39Z)
• Geometrically Principled Connections in Graph Neural Networks [66.51286736506658]
  We argue geometry should remain the primary driving force behind innovation in the emerging field of geometric deep learning. We relate graph neural networks to widely successful computer graphics and data approximation models: radial basis functions (RBFs) We introduce affine skip connections, a novel building block formed by combining a fully connected layer with any graph convolution operator.
  arXiv  Detail & Related papers  (2020-04-06T13:25:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.