KGTS: Contrastive Trajectory Similarity Learning over Prompt Knowledge Graph Embedding

Authors: Zhen Chen, Dalin Zhang, Shanshan Feng, Kaixuan Chen, Lisi Chen, Peng Han, Shuo Shang

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on two real-world trajectory datasets demonstrate the superior performance of KGTS over stateof-the-art methods.
Researcher Affiliation Collaboration 1University of Electronic Science and Technology of China 2Aalborg University, Denmark 3Centre for Frontier AI Research, A*STAR, Singapore 4Institute of High-Performance Computing, A*STAR, Singapore
Pseudocode No The paper includes a framework diagram (Figure 1) and mathematical equations, but no explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology.
Open Datasets Yes We adopt two popular large benchmark datasets for trajectory analysis in our experiments, namely Geo Life (Zheng, Xie, and Ma 2010) and Porto (Moreira Matias et al. 2016).
Dataset Splits Yes For both datasets, we randomly chose trajectories to keep the training, validation, and test ratio approximately as 1:1:1.
Hardware Specification Yes All experiments are conducted with Ge Force RTX 3090 GPU.
Software Dependencies No The paper mentions 'Adam optimizer' but does not provide specific version numbers for software dependencies or libraries.
Experiment Setup Yes The margin γ in Eq. 6 is set to 12. We then train the trajectory embedding module using unsupervised contrastive learning with the loss function in Eq. 12. The hyperparameter τ in Eq. 12 is set to 0.05. Both phases are trained with the Adam optimizer and a learning rate of 0.0001.