Attributed Graph Modeling with Vertex Replacement Grammars

  title={Attributed Graph Modeling with Vertex Replacement Grammars},
  author={Satyaki Sikdar and Neil Shah and Tim Weninger},
  journal={Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
Recent work at the intersection of formal language theory and graph theory has explored graph grammars for graph modeling. However, existing models and formalisms can only operate on homogeneous (i.e., untyped or unattributed) graphs. We relax this restriction and introduce the Attributed Vertex Replacement Grammar (AVRG), which can be efficiently extracted from heterogeneous (i.e., typed, colored, or attributed) graphs. Unlike current state-of-the-art methods, which train enormous models over… 

Figures and Tables from this paper



Modeling Graphs with Vertex Replacement Grammars

This work revises a different graph grammar formalism called Vertex Replacement Grammars (VRGs), and shows that a variant of the VRG called Clustering-based Node Replacement Grammar (CNRG) can be efficiently extracted from many hierarchical clusterings of a graph.

Growing Graphs from Hyperedge Replacement Graph Grammars

This paper shows that a graph's clique tree can be used to extract a hyperedge replacement grammar, and shows that the generative graph model is able to preserve these local graph substructures when generating new graphs and performs well on new and difficult tests of model robustness.

Learning Hyperedge Replacement Grammars for Graph Generation

A new approach that learns the building blocks of graphs that can be used to understand and generate new realistic graphs is developed and evaluated, and it is shown that a Hyperedge Replacement Grammar (HRG) can be extracted from the clique tree.

Towards Interpretable Graph Modeling with Vertex Replacement Grammars

It is shown that KT-grammars can be efficiently extracted from a graph and that these grammars encode meaningful patterns that represent the dynamics of the real-world system.

Scale-Free, Attributed and Class-Assortative Graph Generation to Facilitate Introspection of Graph Neural Networks

This work proposes an intuitive and flexible scalefree graph generation model, CaBaM, which enables simulation of class-assortative and attributed graphs via the well-known BarabasiAlbert model, and shows empirically and theoretically how this model can easily describe a variety of graph types, while imbuing the generated graphs with the necessary ingredients for attribute, topology, and label-aware semi-supervised node-classification.

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

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.

DDGK: Learning Graph Representations for Deep Divergence Graph Kernels

The experimental results show that Deep Divergence Graph Kernels can learn an unsupervised alignment between graphs, and that the learned representations achieve competitive results when used as features on a number of challenging graph classification tasks.

The Infinity Mirror Test for Graph Models

It is shown that several conventional graph models degenerate in exciting and informative ways, and these observed degenerative patterns are clues to the future development of better graph models.

How Powerful are Graph Neural Networks?

This work characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures, and develops a simple architecture that is provably the most expressive among the class of GNNs.

Attributed graph models: modeling network structure with correlated attributes

This work presents the Attributed Graph Model (AGM) framework, a framework to jointly model network structure and vertex attributes, and demonstrates the efficiency and accuracy of this framework on two large real-world networks.