Hypertron: Explicit Social-Temporal Hypergraph Framework for Multi-Agent Forecasting

Authors: Yu Tian, Xingliang Huang, Ruigang Niu, Hongfeng Yu, Peijin Wang, Xian Sun

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on several challenging real-world trajectory forecasting datasets show that Hypertron outperforms a wide array of stateof-the-art methods while saving over 60% parameters and reducing 30% inference time.
Researcher Affiliation Academia 1Key Laboratory of Network Information System Technology, Aerospace Information Research Institute, Chinese Academy of Sciences 2 School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences
Pseudocode No The paper does not contain a clearly labeled pseudocode or algorithm block.
Open Source Code No The paper does not provide any explicit statement about releasing source code for the described methodology or a link to a code repository.
Open Datasets Yes To evaluate our methods, we conduct experiments on three publicly examined datasets: The ETH/UCY datasets and the Stanford Drone Dataset.
Dataset Splits No The paper does not specify exact train/validation/test split percentages or sample counts for the datasets.
Hardware Specification Yes To measure the inference time, we use a V100 GPU.
Software Dependencies No The paper mentions using 'Adam optimizer' but does not specify software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions).
Experiment Setup Yes We train the Hypertron with Adam optimizer, and the initial learning rate is 0.001. The number of hyperedges in the social hypergraph is set to 32, and each hyperedge ei s indicates the social correlation of the i-th agent with others. Similarly, the counterpart of the temporal hypergraph is set to 20, and each ej t indicates the temporal correlation of the agent in the j-th timestep with others.