Learning Graphical State Transitions

By Daniel D. Johnson. 2016

98 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

A Survey of Machine Learning for Big Code and Naturalness (2017, methodology): “We refer the interested reader to the related work section of Johnson [98] for a discussion of recent models in the machine-learning literature.”
Relational inductive biases, deep learning, and graph networks (2018, background): “…Nowak et al., 2017; Dai et al., 2017), boolean satisﬁability (Selsam et al., 2018), program representation and veriﬁcation (Allamanis et al., 2018; Li et al., 2016), modeling cellular automata and Turing machines (Johnson, 2017), and performing inference in graphical models (Yoon et al., 2018).”
Graphite: Iterative Generative Modeling of Graphs (2018, background): “[17] and [21] generate graphs as latent representations learned directly from data.”
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models (2018, methodology): “Note that the DeepGMG algorithm (Li et al., 2018) and the related prior work of Johnson 2017 can also be viewed as deep autoregressive models of graphs.”
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders (2018, neutral): “The closest work to ours is by Johnson (2017), who incrementally constructs a probabilistic (multi)graph as a world representation according to a sequence of input sentences to answer a query.”
Learning Deep Generative Models of Graphs (2018, methodology): “…our work and (Johnson, 2017) is that our goal in this paper is to learn and represent unconditional or conditional densities on a space of graphs given a representative set of graphs, whereas Johnson (2017) is primarily interested in using graphs as intermediate representations in reasoning tasks.”
GraphRNN: A Deep Generative Model for Graphs (2018, methodology): “Note that the DeepGMG algorithm (Li et al., 2018) and the related prior work of Johnson 2017 can also be viewed as deep autoregressive models of graphs.”
Multi-objective de novo drug design with conditional graph generative model (2018, methodology): “process, making the SMILES string a less preferable representation compared to molecular graphs. Research in deep learning has recently enabled the direct generation of molecular graphs. Johnson et al[20] proposed a sequential generation approach for graphs. Though their implementation is mainly for”
FSPool: Learning Set Representations with Featurewise Sort Pooling (2019, background): “However, for the purposes of starting the model as similarly as possible to the sum pooling baseline on CLEVR and on the graph classiﬁcation datasets, we initialise ¯ W to a matrix of all 1s on them.”
MolGAN: An implicit generative model for small molecular graphs (2018, methodology): “…Hamilton et al., 2017), training deep generative models directly on graph representations becomes a feasible alternative that has been explored in a range of recent works (Kipf & Welling, 2016; Johnson, 2017; Grover et al., 2019; Li et al., 2018b; Simonovsky & Komodakis, 2018; You et al., 2018).”
Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration (2018, methodology): “We use the binary cross entropy loss following [19] to train the GCN, where the input is P τ i and the goal is to generate gτ .”
Edge-Labeling Graph Neural Network for Few-Shot Learning (2019, background): “Johnson [43] introduced the Gated Graph Transformer Neural Network (GGT-NN) for”
Variational Reasoning for Question Answering with Knowledge Graph (2017, background): “ere is no explicit traversal over the KG. Graph embedding: Recently, researchers have built deep architectures to embed structured data, such as trees [24,25,26] or graphs [27,28,29]. Also some works [9,30] extend it to sequential case like multi-step reasoning. However, these approaches only work o”
Learning Dynamic Belief Graphs to Generalize on Text-Based Games (2020, methodology): “Johnson [21] construct graphs from text data using gated graph transformer neural networks.”
Learning Discrete Structures for Graph Neural Networks (2019, methodology): “ems such as spring systems (Kipf et al., 2018). Contrary to LDS, the method is specic to dynamical interacting systems, is unsupervised, and uses a variational encoder-decoder. Finally, we note that Johnson (2017) proposed a fully dierentiable neural model able to process and produce graph structure”
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos (2018, methodology): “Inspired by recent frameworks using neural networks for graph optimization [17, 52], we formulate the reference edge model by proposing a hierarchical entity-action pointer network for reference resolution, based on Ptr-Net [48].”
Constrained Graph Variational Autoencoders for Molecule Design (2018, methodology): “In addition, we combine Johnson’s ingredients with a VAE that produces a meaningful latent space to enable continuous graph optimization [8].”
Graph Classification via Deep Learning with Virtual Nodes (2017, background): “There has been a sizable rise of learning graph representation in the past few years [ Bronstein et al. , 2016; Bruna et al. , 2014; Henaff et al. , 2015; Johnson, 2017; Li et al. , 2016; Niepert et al. , 2016; Schlichtkrull et al. , 2017 ] .”