Form follows Function: Text-to-Text Conditional Graph Generation based on Functional Requirements

Peter Zachares, Vahan Hovhannisyan, Alan Mosca, Yarin Gal

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Generative Modelling, Graph Structured Data, Multimodal Conditional Generation, Molecule Generation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: This paper proposes a new problem setting, graph generation conditioned on functional requirements, and a novel method to improve the quality of generated graphs.

Abstract: This work focuses on the novel problem setting of generating graphs conditioned on a description of the graph's functional requirements in a downstream task. We pose the problem as a text-to-text generation problem and focus on the approach of fine-tuning a pretrained large language model (LLM) to generate graphs. We propose an inductive bias which incorporates information about the structure of the graph into the LLM's generation process by incorporating message passing layers into an LLM's architecture. To evaluate our proposed method, we design a novel set of experiments using publicly available and widely studied molecule and knowledge graph data sets. Results suggest our proposed approach generates graphs which more closely meet the requested functional requirements, outperforming baselines developed on similar tasks by a statistically significant margin.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1246