# Multi-Modal Fusion Frameworks of Subgraph-Optimized Graph Autoencoder for Molecular Property Prediction

## TL;DR

This paper introduces a new framework for predicting molecular properties using subgraph-optimized graph autoencoders and multimodal fusion strategies.

## Contribution

The novel contribution is the development of TurboGAE, a subgraph-optimized graph autoencoder, and effective multimodal fusion strategies for molecular property prediction.

## Key findings

- TurboGAE effectively captures substructure features impacting molecular properties.
- Multimodal fusion strategies align intermodal features during pretraining, leveraging each modality's strengths.
- The proposed methods show excellent performance on downstream molecular property prediction tasks.

## Abstract

Molecular property
prediction refers to predicting the properties
of a given molecular representation. This task is of great significance
in fields such as drug design and has garnered widespread attention
from researchers. For molecular property prediction, the quality of
feature learning plays a decisive role in model performance. Although
existing molecular graph models can extract effective feature representations
from graph structures, how to better utilize these features across
different learning tasks remains an important challenge. This paper
proposes a subgraph-optimized Graph Autoencoder (TurboGAE) and several
multimodal fusion strategies. By introducing a subgraph-level graph
tokenizer, TurboGAE more effectively captures the impact of substructure
features (within molecular structures) on molecular properties. For
cross-modal molecular features, a rational and effective multimodal
feature fusion strategy can align intermodal features during the pretraining
phase, leveraging the unique strengths of each modality. The proposed
methods demonstrate excellent performance in experiments on downstream
tasks.