https://github.com/jihyeonseong/som-tp
Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings (AAAI24)
https://github.com/jihyeonseong/som-tp
classification ensemble-learning pooling time-series
Last synced: 9 months ago
JSON representation
Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings (AAAI24)
- Host: GitHub
- URL: https://github.com/jihyeonseong/som-tp
- Owner: jihyeonseong
- Created: 2024-02-14T04:26:39.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-02T06:17:22.000Z (over 1 year ago)
- Last Synced: 2025-02-01T01:11:23.801Z (11 months ago)
- Topics: classification, ensemble-learning, pooling, time-series
- Language: Python
- Homepage:
- Size: 1.3 MB
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings (AAAI24)
* This is the author code implements "Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings," a paper accepted at AAAI 2024.
* It builds upon the official code of [DTP github](https://github.com/donalee/DTW-Pool) and [softDTW github](https://github.com/Maghoumi/pytorch-softdtw-cuda) based on PyTorch.
* For further details, please refer to the original [DTP](https://arxiv.org/abs/2104.02577) and [softDTW](https://arxiv.org/abs/1703.01541) papers.
## Overview
In Time Series Classification (TSC), temporal pooling methods that consider sequential information have been proposed. However, we found that each temporal pooling has a distinct mechanism, and can perform better or worse depending on time series data. We term this fixed pooling mechanism a single perspective of temporal poolings. In this paper, we propose a novel temporal pooling method with diverse perspective learning: Selection over Multiple Temporal Poolings (SoM-TP).
* We investigate data dependency arising from distinct perspectives of existing temporal poolings.
* We propose SoM-TP, a new temporal pooling method that fully utilizes the diverse temporal pooling mechanisms through an MCL-inspired selection ensemble.
* We employ an attention mechanism to enable a non-iterative ensemble in a single classifier.
* We define DPLN and perspective loss as a regularizer to promote diverse pooling selection.
## Running the codes
### STEP 1. Download the benchmark datsets for time series classification
* The datasets can be downloaded form the [UCR/UEA repository](https://www.timeseriesclassification.com/).
* Create a directory named "data" and store downloaded datasets within it.
### STEP 2. Train the CNN classifier with various temporal poolings including SoM-TP
For traditional temporal poolings,
```
python main.py --model=ConvPool --pool=DTP
```
and for SoM-TP
```
python main.py --model=SoMTP
```
### STEP 3. Run LRP (Layer-wise Relevance Propagation: XAI input attribution method)
For traditional temporal poolings,
```
python LRP.py --model=ConvPool --pool=DTP
```
and for SoM-TP
```
python LRP.py --model=SoMTP
```
### SoM-TP performance
1. Comparison with traditional temporal poolings
2. Comparison with advanced TSC methods
3. SoM-TP dynamic selection
4. LRP comparison
## Citation
```
@article{Seong_Kim_Choi_2024,
title={Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings}, volume={38},
url={https://ojs.aaai.org/index.php/AAAI/article/view/28743}, DOI={10.1609/aaai.v38i8.28743},
number={8},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
author={Seong, Jihyeon and Kim, Jungmin and Choi, Jaesik}, year={2024}, month={Mar.}, pages={8948-8956} }
```