Could Chemical LLMs benefit from Message Passing

• URL: http://arxiv.org/abs/2405.08334v2
• Date: Mon, 26 Aug 2024 08:24:14 GMT
• Title: Could Chemical LLMs benefit from Message Passing
• Authors: Jiaqing Xie, Ziheng Chi,
• Abstract summary: We propose two strategies to evaluate whether an information integration can enhance the performance: contrast learning and fusion. Our empirical analysis reveals that the integration approaches exhibit superior performance compared to baselines when applied to smaller molecular graphs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrained language models (LMs) showcase significant capabilities in processing molecular text, while concurrently, message passing neural networks (MPNNs) demonstrate resilience and versatility in the domain of molecular science. Despite these advancements, we find there are limited studies investigating the bidirectional interactions between molecular structures and their corresponding textual representations. Therefore, in this paper, we propose two strategies to evaluate whether an information integration can enhance the performance: contrast learning, which involves utilizing an MPNN to supervise the training of the LM, and fusion, which exploits information from both models. Our empirical analysis reveals that the integration approaches exhibit superior performance compared to baselines when applied to smaller molecular graphs, while these integration approaches do not yield performance enhancements on large scale graphs.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.