Explain Temporal Black-Box Models via Functional Decomposition

Authors: Linxiao Yang, Yunze Tong, Xinyue Gu, Liang Sun

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the effectiveness of our approach in a wide range of time series applications, including anomaly detection, classification, and forecasting, showing its superior performance to the state-of-the-art algorithms.
Researcher Affiliation Collaboration 1DAMO Academy, Alibaba Group, Hangzhou, China 2Department of Computer Science and Technology, Zhejiang University, Hangzhou, China.
Pseudocode No The paper describes the proposed method using mathematical formulations and prose but does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code No The paper does not provide any explicit statements about releasing open-source code for the described methodology, nor does it include links to a code repository.
Open Datasets Yes Large Kitchen Appliances dataset is a public benchmark dataset from UCR 1, which contains 375 training samples and 375 testing samples. (footnote 1 points to https://www.cs.ucr.edu/~eamonn/time_series_data/)
Dataset Splits Yes We randomly split the dataset into three parts, i.e., training set with 14942 samples, validation set with 3448 samples, and test set with 4598 samples.
Hardware Specification No The paper does not explicitly describe the specific hardware used (e.g., CPU/GPU models, memory) to run its experiments. Table 6 lists LSTM configurations but no hardware details.
Software Dependencies No The paper mentions optimizers like 'Adam' and models like 'LSTM' but does not specify software dependencies with version numbers (e.g., 'Python 3.x', 'PyTorch 1.x').
Experiment Setup Yes The configuration of LSTMs as black-box models in each task is summarized in Table 6. Parameters include Latent size (e.g., 20, 200, 120), # layers (e.g., 3, 4), Drop out (e.g., 0.4, 0.6), Adam learning rate (e.g., 0.01, 0.002, 0.001), and epoch (e.g., 100, 200, 300).