Conditional Information Bottleneck-Based Multivariate Time Series Forecasting

Authors: Xinhui Li, Liang Duan, Lixing Yu, Kun Yue, Yuehua Li

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical investigations on authentic datasets underscore the superiority of our proposed approach over other cuttingedge competitors. Our code is available at https: //github.com/Xinhui-Lee/CIB-MTSF. We conduct extensive experiments on 9 real-world datasets, as outlined in [Huang et al., 2024], including ETT datasets (ETTh1, ETTh2, ETTm1, ETTm2), Weather, Traffic, Electricity, ILI, and Exchange Rate. In all experiments, we adopt the same train/val/test split ratio of 6:2:2 for ETT datasets and 7:1:2 for others. We adopt MSE and mean absolute error (MAE) to evaluate the effectiveness of our method.
Researcher Affiliation Academia Xinhui Li 1,2 , Liang Duan 1,2 , Lixing Yu 1,2 , Kun Yue 1,2 and Yuehua Li 3 1 Yunnan Key Laboratory of Intelligent Systems and Computing, Yunnan University, Kunming, China 2 School of Information Science and Engineering, Yunnan University, Kunming, China 3 School of Earth Science, Yunnan University, Kunming, China EMAIL, EMAIL
Pseudocode Yes Algorithm 1 CIB-based MTS forecasting Input: X: historical MTS data Parameters: P: length of patches, T: total training epochs, lr: learning rate, ϕ: parameters of encoder, θ: parameters of variational bound, ξ: parameters of forecasting head Output: ˆX: forecasting results 1: Divide X into M overlapped patches Xp 2: Initialize ϕ, θ, and ξ 3: for t = 1 to T do 4: Z qϕ(Z|XP ) 5: Calculate Lk by Eq. (14) // Constraint on encoder 6: Generate samples Z+ i and Z i 7: Calculate Lc by Eq. (9) // Inter-series correlations 8: Ls 0 9: for k = 3 to M do 10: Calculate Iθ(Zik; Zik 1|Zik 2, . . . , Zi1) 11: Ls Ls + Iθ(Zik; Zik 1|Zik 2, . . . , Zi1) 12: end for 13: Ls Ls/(M 2) // Constraint on time coherences 14: ˆX fξ(Z) // Generating forecasting results 15: Calculate Lm by Eq. (20) // MSE loss 16: L Lm + α1Lk + α1Lc α2Ls 17: ϕ ϕ lr L // Updating parameters 18: θ θ lr L 19: ξ ξ lr L 20: end for 21: return ˆX
Open Source Code Yes Our code is available at https: //github.com/Xinhui-Lee/CIB-MTSF.
Open Datasets Yes We conduct extensive experiments on 9 real-world datasets, as outlined in [Huang et al., 2024], including ETT datasets (ETTh1, ETTh2, ETTm1, ETTm2), Weather, Traffic, Electricity, ILI, and Exchange Rate.
Dataset Splits Yes In all experiments, we adopt the same train/val/test split ratio of 6:2:2 for ETT datasets and 7:1:2 for others.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper mentions parameters like 'P: length of patches, T: total training epochs, lr: learning rate' and hyperparameters 'α1' and 'α2' in Algorithm 1 and Section 4.4, but does not provide their concrete values in the main text. The only specific setting for experiments is 'the input sequence length L is set to 96 for Exchange, 60 for ILI, and 336 for others' which are dataset characteristics, not model hyperparameters.