Graph Generation is an important research area with significant applications in drug and material designs.
Source: Graph Deconvolutional Generation
Based on this, we develop a novel autoregressive model, named BiGG, that utilizes this sparsity to avoid generating the full adjacency matrix, and importantly reduces the graph generation time complexity to $O((n + m)\log n)$.
We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images.
Ranked #3 on Scene Graph Generation on Visual Genome
We provide a new graph generator, based on a "forest fire" spreading process, that has a simple, intuitive justification, requires very few parameters (like the "flammability" of nodes), and produces graphs exhibiting the full range of properties observed both in prior work and in the present study.
We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model.
Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry.
Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences.
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e. g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach".
Ranked #1 on Scene Graph Generation on Visual Genome
We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A.
Ranked #2 on Scene Graph Generation on Visual Genome
Our model generates graphs one block of nodes and associated edges at a time.