GitHub

Adaptive Spectral-Temporal GNN for Molecular Toxicity Prediction

A graph neural network architecture combining spectral convolution with adaptive filtering and temporal curriculum learning for multi-task molecular toxicity prediction on the Tox21 dataset. This work ...
IEEE

Cross-Architecture Contrastive Learning for Few-Shot Hyperspectral Image Classification

Abstract: Hyperspectral image classification is a fundamental task in remote sensing with broad applications in precision agriculture, environmental monitoring, and related fields. However, existing ...
IEEE

RRAM-Based Spectral-Domain Convolution Accelerator for Reliable and Energy-Efficient CNN Inference

Abstract: The growing computational demands of convolutional neural networks (CNNs) have motivated the use of spectral-domain inference as an alternative to costly spatial-domain convolutions. In this ...
GitHub

DTA-GNN: Target-Specific Binding Affinity Dataset Builder and GNN Trainer

Figure 1. DTA-GNN workflow: clean data from ChEMBL, molecular graph conversion, scaffold-aware splitting, and GNN training. Dataset building and GNN training are done via the Python API or Web UI. The ...