LIC-GAN: Language Information Conditioned Graph Generative GAN Model
Preprint
Abstract
Deep generative models for Natural Language data offer a new angle on the problem of graph synthesis: by optimizing differentiable models that directly generate graphs, it is possible to side-step expensive search procedures in the discrete and vast space of possible graphs. We introduce LIC-GAN, an implicit, likelihood-free generative model for small graphs that circumvents the need for expensive graph matching procedures. Our method takes as input a natural language query and using a combination of language modelling and Generative Adversarial Networks (GANs) and returns a graph that closely matches the description of the query. We combine our approach with a reward network to further enhance the graph generation with desired properties. Our experiments, show that LIC-GAN does well on metrics such as PropMatch and Closeness getting scores of 0.36 and 0.48. We also show that LIC-GAN performs as good as ChatGPT, with ChatGPT getting scores of 0.40 and 0.42. We also conduct a few experiments to demonstrate the robustness of our method, while also highlighting a few interesting caveats of the model.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- A Survey on Graph Representation Learning MethodsACM Transactions on Intelligent Systems and Technology, 2024
- Potential Use of Chat GPT in Global WarmingAnnals of Biomedical Engineering, 2023
- Generative Adversarial Reward Learning for Generalized Behavior Tendency InferenceIEEE Transactions on Knowledge and Data Engineering, 2022
- Bert for Question Answering applied on Covid-19Procedia Computer Science, 2022
- Learning to Generate Scene Graph from Natural Language Supervision2021
- Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic DiagnosisProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Meta-Sim: Learning to Generate Synthetic Datasets2019
- PlanITACM Transactions on Graphics, 2019
- Automatic Chemical Design Using a Data-Driven Continuous Representation of MoleculesACS Central Science, 2018
- Geometric Deep Learning: Going beyond Euclidean dataIEEE Signal Processing Magazine, 2017