SpecAR-Net: Spectrogram Analysis and Representation Network for Time Series

Authors: Yi Dong, Liwen Zhang, Youcheng Zhang, Shi Peng, Wen Chen, Zhe Ma

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that the Spec AR-Net achieves excellent performance on 5 major downstream tasks i.e., classification, anomaly detection, imputation, longand shortterm forecasting. To verify the effectiveness and superiority of Spec AR-Net, a comprehensive set of experiments is conducted over 5 mainstream tasks
Researcher Affiliation Industry Yi Dong1 , Liwen Zhang1 , Youcheng Zhang1 , Shi Peng1 , Wen Chen1 and Zhe Ma1 1Intelligent Science & Technology Academy of CASIC, Beijing, China {dongyi0552, lwzhang9161}@126.com, {youcheng17, mazhe thu}@163.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code and appendix are available at https://github.com/Dongyi2go/Spec AR Net.
Open Datasets Yes The data used in this experiment is sourced from the UAE dataset (10 subsets) [Bagnall et al., 2018]... 5 widely-used datasets are employed, i.e., SMD [Su et al., 2019], MSL and SMAP [Hundman et al., 2018], SWa T [Mathur and Tippenhauer, 2016], and PSM [Abdulaal et al., 2021]... In the long-term forecasting (LF) task, a set of benchmark datasets were utilized, including ETT [Zhou et al., 2021b], Electricity, Traffic, Weather, Exchange Rate [Lai et al., 2018a] and ILI (see download links in Appendix)... M4 dataset [Makridakis et al., 2018].
Dataset Splits No The paper describes input and prediction lengths, and masking rates, but does not specify explicit train/validation/test dataset splits (e.g., percentages or sample counts for each split).
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory used for running the experiments.
Software Dependencies No The paper does not provide specific software dependency details with version numbers (e.g., Python version, library versions like PyTorch or TensorFlow).
Experiment Setup Yes In the experiments, the input past length was set to 96, with ILL for 36. The prediction lengths is [96, 192, 336, 720], with ILI for [24, 36, 48, 60]. Random masking with masking rates of [12.5%, 25%, 37.5%, 50%] was used to simulate missing values. MSE is used as loss function... Spec AR-Net was conducted by introducing a order-preserving into the loss function... window lengths are set as [8, 16, 24] in this paper.