Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913194168025088 |
|---|---|
| author | Xiong, Haoyi Li, Xuhong Zhang, Xiaofei Chen, Jiamin Sun, Xinhao Li, Yuchen Sun, Zeyi Du, Mengnan |
| author_facet | Xiong, Haoyi Li, Xuhong Zhang, Xiaofei Chen, Jiamin Sun, Xinhao Li, Yuchen Sun, Zeyi Du, Mengnan |
| contents | Given the complexity and lack of transparency in deep neural networks (DNNs), extensive efforts have been made to make these systems more interpretable or explain their behaviors in accessible terms. Unlike most reviews, which focus on algorithmic and model-centric perspectives, this work takes a "data-centric" view, examining how data collection, processing, and analysis contribute to explainable AI (XAI). We categorize existing work into three categories subject to their purposes: interpretations of deep models, referring to feature attributions and reasoning processes that correlate data points with model outputs; influences of training data, examining the impact of training data nuances, such as data valuation and sample anomalies, on decision-making processes; and insights of domain knowledge, discovering latent patterns and fostering new knowledge from data and models to advance social values and scientific discovery. Specifically, we distill XAI methodologies into data mining operations on training and testing data across modalities, such as images, text, and tabular data, as well as on training logs, checkpoints, models and other DNN behavior descriptors. In this way, our study offers a comprehensive, data-centric examination of XAI from a lens of data mining methods and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04374 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective Xiong, Haoyi Li, Xuhong Zhang, Xiaofei Chen, Jiamin Sun, Xinhao Li, Yuchen Sun, Zeyi Du, Mengnan Artificial Intelligence Machine Learning Given the complexity and lack of transparency in deep neural networks (DNNs), extensive efforts have been made to make these systems more interpretable or explain their behaviors in accessible terms. Unlike most reviews, which focus on algorithmic and model-centric perspectives, this work takes a "data-centric" view, examining how data collection, processing, and analysis contribute to explainable AI (XAI). We categorize existing work into three categories subject to their purposes: interpretations of deep models, referring to feature attributions and reasoning processes that correlate data points with model outputs; influences of training data, examining the impact of training data nuances, such as data valuation and sample anomalies, on decision-making processes; and insights of domain knowledge, discovering latent patterns and fostering new knowledge from data and models to advance social values and scientific discovery. Specifically, we distill XAI methodologies into data mining operations on training and testing data across modalities, such as images, text, and tabular data, as well as on training logs, checkpoints, models and other DNN behavior descriptors. In this way, our study offers a comprehensive, data-centric examination of XAI from a lens of data mining methods and applications. |
| title | Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.04374 |