Processing directed acyclic graphs with recursive neural networks
By Monica Bianchini, Marco Gori, Franco Scarselli. 2001
33 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- William L. Hamilton
- Jure Leskovec
- Rex Ying
- Jiaxuan You
- Alessio Micheli
- Christopher Morris
- Xiang Ren
- Yoshua Bengio
In Molecular Biology
- Rex Ying
- William L. Hamilton
- Jiaxuan You
- Jure Leskovec
- Alessio Micheli
- Christopher Morris
- Xiang Ren
- Barbara Hammer
Citations in the corpus
- Hierarchical Graph Representation Learning with Differentiable Pooling (2018, methodology): “network (GNN) models have been proposed in recent years, including methods inspired by convolutional neural networks [5, 8, 11, 16, 21, 24, 29, 36], recurrent neural networks [25], recursive neural networks [1, 30] and loopy belief propagation [7].”
- Tree2Vector: Learning a Vectorial Representation for Tree-Structured Data (2018, methodology): “networks (GNNs) [46], which extend multilayer perceptron into the domain of graphs (cyclic and acyclic), and recursive neural networks (RNNs) [47], with an input domain consisting of directed acyclic graphs, which are mapped into vectors of reals.”
- Neural networks for relational learning: an experimental comparison (2011, methodology): “Moreover, also the use of particular transition function can simplify the elaboration of some particular kind of graphs, for instance non– positional graphs [Bianchini et al., 2001].”
- The Graph Neural Network Model (2009, unknown): “Similarly, using a preprocessing phase, it is possible to handle certain types of cyclic graphs [24].”
- Neural methods for non-standard data (2004, methodology): “Several generalizations of basic recursive models to better fit these type data have been proposed: recursive networks for acyclic graphs ([7] and (Bian-chini/Maggini/Sarti/Scarselli, this volume)), bicausal networks for protein secondary structure prediction [4], an extension of recursive networks…”
- Neural Network for Graphs: A Contextual Constructive Approach (2009, methodology): “1The treatment of DAG by RNN is introduced in [18].”