Conference Papers Year : 2022

Molecular Activity Prediction Based on Graph Attention Network

Abstract

Spatial convolutional models of Graph Neural Networks (GNNs) updates embeddings of nodes by the neighborhood aggregation, it has obvious advantages in reducing time complexity and improving accuracy. Therefore, it is a very important task to change the way of neighborhood aggregation to learn better node embeddings. Attention mechanisms are usually used to assign trainable weights to nodes in neighborhood aggregation, so that the node influence can also participate in the process of neighborhood aggregation. We propose the ATT-MLP model that combines attention mechanism and multi-layer perception(MLP), and applys node attention weights to graph pooling. Experiments on graph prediction show that our algorithm performs better than other baselines on commonly used datasets.
Fichier principal
Vignette du fichier
537972_1_En_42_Chapter.pdf (492.56 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04666418 , version 1 (01-08-2024)

Licence

Identifiers

Cite

Xiaowei Cao, Tiwen Wang, Ruohui Cheng, Jingyi Ding. Molecular Activity Prediction Based on Graph Attention Network. 5th International Conference on Intelligence Science (ICIS), Oct 2022, Xi'an, China. pp.395-401, ⟨10.1007/978-3-031-14903-0_42⟩. ⟨hal-04666418⟩
12 View
2 Download

Altmetric

Share

More