Abstract: In unsupervised graph anomaly detection, existing methods usually focus on detecting outliers by learning local context information of nodes, while often ignoring the importance of global ...
Abstract: Using skeletal information to model and recognize human actions is currently a hot research subject in the realm of Human Action Recognition (HAR). Graph Convolutional Networks (GCN) have ...
This is the repository for the paper GraphXForm: Graph transformer for computer-aided molecular design, published in Digital Discovery. The terminal output will show under which subdirectory (named ...
This is the official implementation for our NeurIPS 2024 paper "Can Graph Learning Improve Planning in LLM-based Agents?" [中文] For running LLM's direct inference or GraphSearch, our codes are ...
On 17 August, a report titled "The Chinese Dam Threatening the World’s Most Endangered Ape" was published by Inside Climate News, detailing various aspects of human rights violations surrounding the ...