Tech Xplore

AI model can manipulate time to make better predictions in a wide range of fields

In the world around us, many things exist in the context of time: a bird's path through the sky is understood as different ...
IEEE

Probability-Based Graph Embedding Cross-Domain and Class Discriminative Feature Learning for Domain Adaptation

Abstract: Feature-based domain adaptation methods project samples from different domains into the same feature space and try to align the distribution of two domains to learn an effective transferable ...
C&EN

Sequence Divergence in the Arginase Domain of Ornithine Decarboxylase/Arginase in Fusobacteriacea Leads to Loss of Function in Oral Associated Species

Department of Chemistry, University of British Columbia, Okanagan Campus, 3247 University Way, Kelowna V1V 1V7, Canada ...
The Lancet

The potential of kidney transplantation to reduce mortality from chronic kidney disease: a global, cross-sectional, modelling study

aCenter for Health Equity in Surgery and Anesthesia, Department of Surgery, University of California, San Francisco, San Francisco, CA, USA bDepartment of Medicine, University of Alberta, Edmonton, AB ...
IEEE

Frequency Domain-Oriented Complex Graph Neural Networks for Graph Classification

Abstract: Graph neural networks (GNNs) could directly deal with the data of graph structure. Current GNNs are confined to the spatial domain and learn real low-dimensional embeddings in graph ...
GitHub

Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptation (WWW-2025).

This is a PyTorch implementation of the GraphATA algorithm, which tries to address the multi-source domain adaptation problem without accessing the labelled source graph. Unlike previous multi-source ...