paper-with-me

Papers

Comparison of Optimised Geometric Deep Learning Architectures, over Varying Toxicological Assay Data Environments

2025-07-22 · Alexander D. Kalian, Lennart Otte, Jaewook Lee, Emilio Benfenati, Jean-Lou C. M. Dorne, Claire Potter, Olivia J. Osborne, Miao Guo, Christer Hogstrand arxiv

Geometric deep learning is an emerging technique in Artificial Intelligence (AI) driven cheminformatics, however the unique implications of different Graph Neural Network (GNN) architectures are poorly explored, for this space. This study compared performances of Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs) and Graph Isomorphism Networks (GINs), applied to 7 different toxicological assay datasets of varying data abundance and endpoint, to perform binary classification of assay activation. Following pre-processing of molecular graphs, enforcement of class-balance and stratification of all datasets across 5 folds, Bayesian optimisations were carried out, for each GNN applied to each assay dataset (resulting in 21 unique Bayesian optimisations). Optimised GNNs performed at Area Under the Curve (AUC) scores ranging from 0.728-0.849 (averaged across all folds), naturally varying between specific assays and GNNs. GINs were found to consistently outperform GCNs and GATs, for the top 5 of 7 most data-abundant toxicological assays. GATs however significantly outperformed over the remaining 2 most data-scarce assays. This indicates that GINs are a more optimal architecture for data-abundant environments, whereas GATs are a more optimal architecture for data-scarce environments. Subsequent analysis of the explored higher-dimensional hyperparameter spaces, as well as optimised hyperparameter states, found that GCNs and GATs reached measurably closer optimised states with each other, compared to GINs, further indicating the unique nature of GINs as a GNN algorithm.

📄 PDF Abstract BibTeX arXiv:2507.17775

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationGraph Neural Network

Similar Papers 제목 키워드 기반

IRX-1D: A Simple Deep Learning Architecture for Remote Sensing Classifications

2020-10-08 · Mahesh Pal, Akshay, B. Charan Teja

We proposes a simple deep learning architecture combining elements of Inception, ResNet and Xception networks. Four new datasets were used for classification with both small and large training samples. Results in terms o…

ClassificationDeep LearningGeneral Classification

GGPT: Geometry Grounded Point Transformer

2026-03-11 · Yutong Chen, Yiming Wang, Xucong Zhang, Sergey Prokudin 외 arxiv

Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limit…

3D ReconstructionPoint Clouds

OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices

2021-06-08 · Stylianos I. Venieris, Ioannis Panopoulos, Iakovos S. Venieris

Radical progress in the field of deep learning (DL) has led to unprecedented accuracy in diverse inference tasks. As such, deploying DL models across mobile platforms is vital to enable the development and broad availabi…

Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs

2020-06-09 · Miguel de Prado, Andrew Mundy, Rabia Saeed, Maurizio Denna 외

The spread of deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN). Works have mainly focused on: i) efficient DNN architectures, ii)…

CPU

Evaluation of Model Selection for Kernel Fragment Recognition in Corn Silage

2020-04-01 · Christoffer Bøgelund Rasmussen, Thomas B. Moeslund

Model selection when designing deep learning systems for specific use-cases can be a challenging task as many options exist and it can be difficult to know the trade-off between them. Therefore, we investigate a number o…

Model Selection