Abstract: In this research, we propose Log2Graph, a new insider threat detection method based on graph convolution neural network (GCN). This method first retrieves the corresponding logs and features ...

Abstract: Complete and accurate traffic data is critical in urban traffic management, planning and operation. In fact, real-world traffic data contains missing values due to multiple factors, such as ...

This repository contains the implementation of DSTFGCN, a deep learning model for traffic flow forecasting.

Researchers have developed AdapGNN, a novel model-agnostic framework that addresses the oversmoothing problem in graph neural ...

This is the PyTorch implementation for DiffKG proposed in the paper DiffKG: Knowledge Graph Diffusion Model for Recommendation, which is accepted by WSDM 2024 Oral. Yangqin Jiang, Yuhao Yang, Lianghao ...

该研究提出一种基于图的CAD辅助方法，可在参数化设计序列中预测下一个建模操作。研究人员将来自汽车领域的真实CATIA V5模型转换为有向无环图（Directed Acyclic Graph，DAG）以捕获特征依赖关系，从而实现直接从结构设计数据中学习。所采用的 该研究提出一种基于图的CAD辅助方法，可在参数化设计序列中预测下一个建模操作。研究人员将来自汽车领域的真实CATIA V5模型转换为有向无 ...

Sunkara et al., 2023 ). After the S P D r rearrangement, a stride-1 convolution is used to mix and compress the channel dimension so that the output channel size remains consistent with the original ...

What about ChatGPT and related large AI Systems? How will they impact us all? As a longtime researcher in AI, I'm excited about the ways in which these new AI systems can improve our healthcare, ...

强化学习（Reinforcement Learning, RL）在设计自适应中的适用性与可扩展性可通过基于图的方法而非刚性的向量或网格方法得以拓展。然而，基于图的方法通常需要大量的模拟才能收敛。为降低机械优化中的模拟工作量，研究人员在强化学习设置中融入了任务特 强化学习（Reinforcement Learning, RL）在设计自适应中的适用性与可扩展性可通过基于图的方法而非刚性的向量或网格方法 ...