Supervised neural networks for the classification of structures

By Alessandro Sperduti, Antonina Starita. 1997

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Gated Graph Sequence Neural Networks (2015, background): “Sperduti & Starita (1997) map graphs to graph vectors then classify using an output neural network.”
The Graph Neural Network Model (2009, neutral): “The neural architectures, which have been suggested for realizing and , include multilayered FNNs [17], [19], cascade correlation [68], and self-organizing maps [20], [69].”
Directional Message Passing for Molecular Graphs (2020, neutral): “GNNs were ﬁrst proposed in the 90s (Baskin et al., 1997; Sperduti & Starita, 1997) and 00s (Gori et al., 2005; Scarselli et al., 2009).”
On the Binding Problem in Artificial Neural Networks (2020, methodology): “MPNNs were initially conceived as a generalization of RNNs to graph-structured inputs (Sperduti and Starita, 1997; Gori et al., 2005) and have since been adapted to consider modern deep neural networks (Li et al.”
Pre-training Graph Neural Networks with Kernels (2018, neutral): “The ﬁrst deﬁnition of neural network for graphs has been proposed in Sperduti and Starita [1997].”
Isometric Transformation Invariant and Equivariant Graph Convolutional Networks (2020, background): “The studies presented by Baskin et al. (1997); Sperduti & Starita (1997); Gori et al. (2005); Scarselli et al. (2008) were the first research works that discussed the concept of GNNs.”
Image Generation from Scene Graphs (2018, methodology): “More closely related to our work are Graph Neural Networks (GNNs) [11, 13, 46] which generalize recursive neural networks [8, 49, 48] to operate on arbitrary graphs.”
A Comprehensive Survey on Graph Neural Networks (2019, background): “Constrained by computational power, earlier research mainly focused on directed acyclic graphs [13], [80].”
Neural Network for Graphs: A Contextual Constructive Approach (2009, methodology): “Hence, we avoid the use of conventional representation rules aimed at defining rooted ordered/positional 3The data set is fully reported in [15] and also available at http://www.di. unipi.it/~micheli/dataset TABLE I TENFOLD CV RESULTS FOR CRCC AND NN4Gs In the original RCC/CRCC experiments [15], [17”
Sequence Learning (2001, methodology): “Within this class we can mention Recurrent CascadeCorrelation [18], a partition algorithm using Radial Basis Functions [68], and Recurrent Neural Trees [60].”
Learning Longer-term Dependencies in RNNs with Auxiliary Losses (2018, background): “Well known approaches include recurrent networks with special structures (El Hihi & Bengio, 1996; Sperduti & Starita, 1997; Frasconi et al., 1998; Socher et al., 2011; Chan et al., 2016), Long Short-Term Memory Networks (Hochreiter & Schmidhuber, 1997; Gers et al., 1999; Graves, 2013), Gated…”
Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings (2019, background): “…Velickovic et al., 2018), and the spectral approaches proposed in, e.g., (Bruna et al., 2014; Defferrard et al., 2016; Kipf & Welling, 2017; Monti et al., 2017)—all of which descend from early work in (Kireev, 1995; Merkwirth & Lengauer, 2005; Sperduti & Starita, 1997; Scarselli et al., 2009).”
Inductive Learning in Symbolic Domains Using Structure-Driven Recurrent Neural Networks (1996, background): “Recently, [ 14 ] proposed a framework for different architectures built of socalled complex recursive neurons.”
The Principled Design of Large-Scale Recursive Neural Network Architectures--DAG-RNNs and the Protein Structure Prediction Problem (2003, background): “…systematically to many large-scale problems, by itself it is not new and can be traced, in more or less obscure form, to a number of publications including Baldi and Chauvin (1996), Bengio and Frasconi (1996), Sperduti and Starita (1997), Goller (1997), LeCun et al. (1998), Frasconi et al. (1998).”