3 papers
cs.LG2024
Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion
Jiasheng Zhang, Deqiang Ouyang, Shuang Liang +1
Predicting missing facts for temporal knowledge graphs (TKGs) is a fundamental task, called temporal knowledge graph completion (TKGC). One key challenge in this task is the imbala…
cs.AI2024
DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
Jiasheng Zhang, Jialin Chen, Menglin Yang +4
Dynamic text-attributed graphs (DyTAGs) are prevalent in various real-world scenarios, where each node and edge are associated with text descriptions, and both the graph structure…
cs.LG2023
Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills
Hongcai He, Anjie Zhu, Shuang Liang +2
Offline meta-reinforcement learning (meta-RL) methods, which adapt to unseen target tasks with prior experience, are essential in robot control tasks. Current methods typically uti…