Differentiable Rule Induction from Raw Sequence Inputs
Authors: Kun Gao, Katsumi Inoue, Yongzhi Cao, Hanpin Wang, Yang Feng
ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate that our method intuitively and precisely learns generalized rules from time series and image data. [...] 5 EXPERIMENTAL RESULTS In this subsection, we evaluate the model on synthetic time series data based on triangular pulse signals and trigonometric signals. [...] In this subsection, we experimentally demonstrate the effectiveness of Neur RL on 13 randomly selected datasets from UCR (Dau et al., 2019). [...] In this subsection, we ask the model to learn rules to describe and discriminate two classes of images from MNIST datasets. [...] We conducted ablation studies using default hyperparameters, except for the one being explored. |
| Researcher Affiliation | Academia | 1Institute of High Performance Computing, Agency for Science, Technology and Research 2National Institute of Informatics 3Key Laboratory of High Confidence Software Technologies, School of Computer Science Peking University |
| Pseudocode | No | The paper describes the architecture and processes mathematically and with diagrams (Fig. 1a, 1b) but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | Yes | B THE LINK OF THE MODEL The model and data can be found here: https://github.com/gaokun12/Neur RL |
| Open Datasets | Yes | In this subsection, we experimentally demonstrate the effectiveness of Neur RL on 13 randomly selected datasets from UCR (Dau et al., 2019), as used by Wang et al. (2019). ... Hoang Anh Dau, Anthony Bagnall, Kaveh Kamgar, Chin-Chia Michael Yeh, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, and Eamonn Keogh. The UCR time series archive. IEEE/CAA Journal of Automatica Sinica, 6(6):1293 1305, 2019. https://www.cs.ucr. edu/ eamonn/time_series_data_2018/. ... In this subsection, we ask the model to learn rules to describe and discriminate two classes of images from MNIST datasets. |
| Dataset Splits | Yes | To test Neur RL s learning capability on a smaller dataset, we set the number of inputs in both the positive and negative classes to two for both the training and test datasets. In each class, the difference between two inputs at each time point is a random number drawn from a normal distribution with a mean of zero and a variance of 0.1. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware used (e.g., GPU models, CPU models, memory specifications) for running its experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions, or other libraries). |
| Experiment Setup | Yes | We set α to 1000 in the whole experiments. ... We set the fixed bias as 0.5. ... In our experiments, we assigned equal weights to finding representations, identifying clusters, and discovering rules by setting λ1 = λ2 = 1. ... We set both the length of each region and the subsequence length to five units, and the number of clusters is set to three in this experiment. ... The number of clusters in this experiment is set to five. The subsequence length and the number of regions vary for each task. We set the number of regions to approximately 10 for time series data. Additionally, the subsequence length is set to range from two to five, depending on the specific subtask. ... The lengths of subsequence and region are both set to three. Besides, the number of clusters is set to five. |