Summary of Beyond Explaining: Xai-based Adaptive Learning with Shap Clustering For Energy Consumption Prediction, by Tobias Clement and Hung Truong Thanh Nguyen and Nils Kemmerzell and Mohamed Abdelaal and Davor Stjelja
Beyond explaining: XAI-based Adaptive Learning with SHAP Clustering for Energy Consumption Prediction
by Tobias Clement, Hung Truong Thanh Nguyen, Nils Kemmerzell, Mohamed Abdelaal, Davor Stjelja
First submitted to arxiv on: 7 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Databases (cs.DB)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach that combines explainable artificial intelligence (XAI) techniques with adaptive learning to enhance energy consumption prediction models, particularly when dealing with data distribution shifts. The method leverages SHAP clustering to provide interpretable explanations for model predictions, and uses these insights to adaptively refine the model, balancing complexity with performance. A three-stage process is introduced: obtaining SHAP values to explain predictions, clustering SHAP values to identify patterns and outliers, and refining the model based on derived characteristics. The approach mitigates overfitting and ensures robustness in handling data distribution shifts. The method is evaluated on a comprehensive dataset of building energy consumption records, as well as two additional datasets to assess transferability to regression and classification problems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a way to make artificial intelligence more understandable by combining it with learning that adapts to changing situations. It uses special techniques called SHAP clustering to explain why AI predictions are correct or not. This helps refine the model, making sure it’s accurate and easy to understand. The approach is tested on energy consumption data from buildings and other types of problems, showing improved performance and understandable explanations. |
Keywords
* Artificial intelligence * Classification * Clustering * Overfitting * Regression * Transferability
