Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning

no code implementations • 4 Dec 2023 • Wei Chen, Huaiyu Wan, Yuting Wu, Shuyuan Zhao, Jiayaqi Cheng, Yuxin Li, Youfang Lin

Temporal knowledge graphs (TKGs) have been identified as a promising approach to represent the dynamics of facts along the timeline.

Contrastive Learning Knowledge Graphs

Listen to Minority: Encrypted Traffic Classification for Class Imbalance with Contrastive Pre-Training

no code implementations • 31 Aug 2023 • Xiang Li, Juncheng Guo, Qige Song, Jiang Xie, Yafei Sang, Shuyuan Zhao, Yongzheng Zhang

Despite some existing learning-based ETC methods showing promising results, three-fold limitations still remain in real-world network environments, 1) label bias caused by traffic class imbalance, 2) traffic homogeneity caused by component sharing, and 3) training with reliance on sufficient labeled traffic.

Pseudo Label Traffic Classification

Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception

no code implementations • 31 Jul 2023 • Yuntao Liu, Qian Huang, Rongpeng Li, Xianfu Chen, Zhifeng Zhao, Shuyuan Zhao, Yongdong Zhu, Honggang Zhang

Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents.

Graph Neural Network