Graph Generation
241 papers with code • 1 benchmarks • 5 datasets
Graph Generation is an important research area with significant applications in drug and material designs.
Source: Graph Deconvolutional Generation
Benchmarks
These leaderboards are used to track progress in Graph Generation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Graph Generation models and implementations
Torque
PISC
WikiGraphs
TRN
Latest papers
EGTR: Extracting Graph from Transformer for Scene Graph Generation
We propose a lightweight one-stage SGG model that extracts the relation graph from the various relationships learned in the multi-head self-attention layers of the DETR decoder.
Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generation
Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs for constructing event temporal graphs, have shown promising results.
SteinGen: Generating Fidelitous and Diverse Graph Samples
Generating graphs that preserve characteristic structures while promoting sample diversity can be challenging, especially when the number of graph observations is small.
3M-Diffusion: Latent Multi-Modal Diffusion for Text-Guided Generation of Molecular Graphs
However, practical applications call for methods that generate diverse, and ideally novel, molecules with the desired properties.
GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
To evaluate and enhance the graph understanding abilities of LLMs, in this paper, we propose a benchmark named GraphInstruct, which comprehensively includes 21 classical graph reasoning tasks, providing diverse graph generation pipelines and detailed reasoning steps.
Neural Graph Generator: Feature-Conditioned Graph Generation using Latent Diffusion Models
iakovosevdaimon/graph-generator
•
•
Graph generation has emerged as a crucial task in machine learning, with significant challenges in generating graphs that accurately reflect specific properties.
Graph Diffusion Policy Optimization
sail-sg/gdpo
•
•
Recent research has made significant progress in optimizing diffusion models for specific downstream objectives, which is an important pursuit in fields such as graph generation for drug design.
Diffusion-based graph generative methods
Being the most cutting-edge generative methods, diffusion methods have shown great advances in wide generation tasks.
SGTR+: End-to-end Scene Graph Generation with Transformer
scarecrow0/sgtr
•
•
Moreover, we design a graph assembling module to infer the connectivity of the bipartite scene graph based on our entity-aware structure, enabling us to generate the scene graph in an end-to-end manner.
Adaptive Self-training Framework for Fine-grained Scene Graph Generation
To this end, we introduce a Self-Training framework for SGG (ST-SGG) that assigns pseudo-labels for unannotated triplets based on which the SGG models are trained.
