Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning
Authors: Sungyong Seo, Chuizheng Meng, Sirisha Rambhatla, Yan Liu
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We apply the proposed framework to both synthetic and real-world spatiotemporal prediction tasks and demonstrate its superior performance with limited observations. |
| Researcher Affiliation | Academia | Sungyong Seo , Chuizheng Meng , Sirisha Rambhatla and Yan Liu University of Southern California, USA {sungyons, chuizhem, sirishar, yanliu.cs}@usc.edu |
| Pseudocode | Yes | Algorithm 1 Spatial derivative module (SDM) ... Algorithm 2 Time derivative module (TDM) ... Algorithm 3 Meta-initialization with auxiliary tasks: Supervision of spatial derivatives ... Algorithm 4 Adaptation on meta-test tasks |
| Open Source Code | No | The paper does not provide an explicit statement or link for open-source code availability for the described methodology. |
| Open Datasets | Yes | For the AQI-CO dataset, we construct 12 meta-test tasks with the carbon monoxide (CO) ppm records from the first week of each month in 2015 at land-based stations. ... For the extreme weather dataset, we select the top-10 extreme weather events with the longest lasting time from the year 1984 and construct a meta-test task from each event with the observed surface temperatures at randomly sampled locations. ... (1) AQI-CO: national air quality index (AQI) observations [Berman, 2017]; (2) Extreme Weather (EW): the extreme weather dataset [Racah et al., 2017]. |
| Dataset Splits | No | The paper describes training with a 'T-shot' setting and evaluation on 'held-out' sequences, but it does not specify explicit train/validation/test splits with percentages or counts, nor does it refer to standard predefined splits for the datasets used that include a validation set. It does not clearly define a separate validation set. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments (e.g., specific GPU/CPU models, memory, or cluster specifications). |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies (e.g., programming languages, libraries, or frameworks). |
| Experiment Setup | No | The paper describes the general approach and module design, including the meta-training algorithms with learning rates α and β. However, it does not provide concrete hyperparameter values (e.g., specific values for α, β, batch size, number of epochs, or detailed network architecture configurations beyond module names) in the main text. |