• Corpus ID: 204509457

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs

@article{Stoehr2019DisentanglingIG,
  title={Disentangling Interpretable Generative Parameters of Random and Real-World Graphs},
  author={Niklas Stoehr and Marc Brockschmidt and Jan Stuehmer and Emine Yilmaz},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.05639}
}
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world graphs requires domain knowledge and time-consuming simulation. While existing deep learning approaches rely on less manual modelling, they offer little interpretability. This work approaches graph generation (decoding) as the inverse of graph… 
A Systematic Survey on Deep Generative Models for Graph Generation
TLDR
An extensive overview of the literature in the field of deep generative models for graph generation is provided and two taxonomies of deep Generative Models for unconditional, and conditional graph generation respectively are proposed.
Interpretable Deep Graph Generation with Node-edge Co-disentanglement
TLDR
A novel variational objective is proposed to disentangle the above three types of latent factors, with novel architecture for node and edge deconvolutions, and Qualitative and quantitative experiments demonstrate the effectiveness of the proposed model and its extensions.
A Graph VAE and Graph Transformer Approach to Generating Molecular Graphs
TLDR
The proposed model builds on graph generative work operating on graphs with edge features, creating a model that offers improved scalability with the number of nodes in a graph and is capable of learning a disentangled, interpretable latent space that represents graph properties through a mapping between latent variables and graph properties.
Deep Graph Generators: A Survey
TLDR
A comprehensive survey on deep learning-based graph generation approaches is conducted and classifies them into five broad categories, namely, autoregressive, autoencoder-based, reinforcement learning- based, adversarial, and flow- based graph generators, providing the readers a detailed description of the methods in each class.
Team “NoConflict” at CASE 2021 Task 1: Pretraining for Sentence-Level Protest Event Detection
An ever-increasing amount of text, in the form of social media posts and news articles, gives rise to new challenges and opportunities for the automatic extraction of socio-political events. In this
Mining the Automotive Industry: A Network Analysis of Corporate Positioning and Technological Trends
The digital transformation is driving revolutionary innovations and new market entrants threaten established sectors of the economy such as the automotive industry. Following the need for monitoring
Mining the Automotive Industry: A Network Analysis of Corporate Positioning and Technological Trends
TLDR
This work presents a method to reveal hierarchical structures of unstructured text content obtained from web scraping that is highly transparent, reproducible and data driven, and could be used to gain complementary insights into innovative strategies of firms and competitive landscapes which would not be detectable by the analysis of web content alone.
Which industries are most severely affected by the COVID-19 pandemic? A data-mining approach to identify industry-specific risks in real-time
While the coronavirus spreads around the world, governments are attempting to reduce contagion rates at the expense of negative economic effects. Market expectations have plummeted, foreshadowing the
The CoRisk-Index: A Data-Mining Approach to Identify Industry-Specific Risk Assessments Related to COVID-19 in Real-Time
While the coronavirus spreads, governments are attempting to reduce contagion rates at the expense of negative economic effects. Market expectations plummeted, foreshadowing the risk of a global
Deep Generative Modeling in Network Science with Applications to Public Policy Research
TLDR
Explores deep generative modeling in network science towards informing key public policy questions in education and research.
...
1
2
...

References

SHOWING 1-10 OF 39 REFERENCES
Learning Deep Generative Models of Graphs
TLDR
This work is the first and most general approach for learning generative models over arbitrary graphs, and opens new directions for moving away from restrictions of vector- and sequence-like knowledge representations, toward more expressive and flexible relational data structures.
Disentangled Graph Convolutional Networks
TLDR
This paper introduces the disentangled graph convolutional network (DisenGCN) and proposes a novel neighborhood routing mechanism, which is capable of dynamically identifying the latent factor that may have caused the edge between a node and one of its neighbors, and accordingly assigning the neighbor to a channel that extracts and convolutes features specific to that factor.
GraphRNN: A Deep Generative Model for Graphs
TLDR
The experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.
NetGAN: Generating Graphs via Random Walks
TLDR
The proposed model is based on a stochastic neural network that generates discrete output samples and is trained using the Wasserstein GAN objective, and is able to produce graphs that exhibit the well-known network patterns without explicitly specifying them in the model definition.
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial
Constrained Graph Variational Autoencoders for Molecule Design
TLDR
A variational autoencoder model in which both encoder and decoder are graph-structured is proposed and it is shown that by using appropriate shaping of the latent space, this model allows us to design molecules that are (locally) optimal in desired properties.
Deep Neural Networks for Learning Graph Representations
TLDR
A novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information directly, and which outperforms other stat-of-the-art models in such tasks.
Walklets: Multiscale Graph Embeddings for Interpretable Network Classification
TLDR
These representations clearly encode multiscale vertex relationships in a continuous vector space suitable for multi-label classification problems and outperforms new methods based on neural matrix factorization, and can scale to graphs with millions of vertices and edges.
Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
TLDR
It is demonstrated that the proposed prior significantly mitigates the trade-off between reconstruction loss and disentanglement over the state of the art and resolves the problem of unidentifiability of the standard VAE normal prior.
GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
TLDR
This work proposes to sidestep hurdles associated with linearization of discrete structures by having a decoder output a probabilistic fully-connected graph of a predefined maximum size directly at once by formulated as a variational autoencoder.
...
1
2
3
4
...