GitHub

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation (WWW 2024)

This is a PyTorch implementation of the GraphCTA algorithm, which tries to address the domain adaptation problem without accessing the labelled source graph. It performs model adaptation and graph ...
IEEE

Domain Adversarial Graph Neural Network based Regional Distributed PV Ultra-Short-term Power Forecasting Considering Data-Scarce Scenarios

Abstract: Accurately forecasting the power generated by regional distributed photovoltaics (DPV) plays a pivotal role in mitigating the potentially adverse impacts of DPV on the distribution network.
IEEE

Dual Graph Cross-Domain Few-Shot Learning for Hyperspectral Image Classification

Abstract: Most domain adaptation (DA) methods focus on the case where the source data (SD) and target data (TD) with the same classes are obtained by the same sensor in cross-scene hyperspectral image ...