Towards Explainable Artificial Intelligence (XAI): A Data Mining
Perspective
- URL: http://arxiv.org/abs/2401.04374v2
- Date: Sat, 13 Jan 2024 06:00:18 GMT
- Title: Towards Explainable Artificial Intelligence (XAI): A Data Mining
Perspective
- Authors: Haoyi Xiong and Xuhong Li and Xiaofei Zhang and Jiamin Chen and Xinhao
Sun and Yuchen Li and Zeyi Sun and Mengnan Du
- Abstract summary: 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, influences of training data, and insights of domain knowledge.
Specifically, we distill XAI methodologies into data mining operations on training and testing data across modalities.
- Score: 35.620874971064765
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- iNNspector: Visual, Interactive Deep Model Debugging [8.997568393450768]
We propose a conceptual framework structuring the data space of deep learning experiments.
Our framework captures design dimensions and proposes mechanisms to make this data explorable and tractable.
We present the iNNspector system, which enables tracking of deep learning experiments and provides interactive visualizations of the data.
arXiv Detail & Related papers (2024-07-25T12:48:41Z) - Data Augmentation in Human-Centric Vision [54.97327269866757]
This survey presents a comprehensive analysis of data augmentation techniques in human-centric vision tasks.
It delves into a wide range of research areas including person ReID, human parsing, human pose estimation, and pedestrian detection.
Our work categorizes data augmentation methods into two main types: data generation and data perturbation.
arXiv Detail & Related papers (2024-03-13T16:05:18Z) - Capture the Flag: Uncovering Data Insights with Large Language Models [90.47038584812925]
This study explores the potential of using Large Language Models (LLMs) to automate the discovery of insights in data.
We propose a new evaluation methodology based on a "capture the flag" principle, measuring the ability of such models to recognize meaningful and pertinent information (flags) in a dataset.
arXiv Detail & Related papers (2023-12-21T14:20:06Z) - Data-centric Graph Learning: A Survey [39.47937127582]
We propose a novel taxonomy based on the stages in the graph learning pipeline.
We analyze some potential problems embedded in graph data and discuss how to solve them in a data-centric manner.
arXiv Detail & Related papers (2023-10-08T03:17:22Z) - ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
We introduce Action-Aware Embodied Learning for Perception (ALP)
ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective.
We show that ALP outperforms existing baselines in several downstream perception tasks.
arXiv Detail & Related papers (2023-06-16T21:51:04Z) - Explaining Explainability: Towards Deeper Actionable Insights into Deep
Learning through Second-order Explainability [70.60433013657693]
Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level.
We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
arXiv Detail & Related papers (2023-06-14T23:24:01Z) - Towards Open-World Feature Extrapolation: An Inductive Graph Learning
Approach [80.8446673089281]
We propose a new learning paradigm with graph representation and learning.
Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
arXiv Detail & Related papers (2021-10-09T09:02:45Z) - An Information-theoretic Approach to Distribution Shifts [9.475039534437332]
Safely deploying machine learning models to the real world is often a challenging process.
Models trained with data obtained from a specific geographic location tend to fail when queried with data obtained elsewhere.
neural networks that are fit to a subset of the population might carry some selection bias into their decision process.
arXiv Detail & Related papers (2021-06-07T16:44:21Z) - Data and its (dis)contents: A survey of dataset development and use in
machine learning research [11.042648980854487]
We survey the many concerns raised about the way we collect and use data in machine learning.
We advocate that a more cautious and thorough understanding of data is necessary to address several of the practical and ethical issues of the field.
arXiv Detail & Related papers (2020-12-09T22:13:13Z) - A Visual Analytics Framework for Explaining and Diagnosing Transfer
Learning Processes [42.57604833160855]
We present a visual analytics framework for the multi-level exploration of the transfer learning processes when training deep neural networks.
Our framework establishes a multi-aspect design to explain how the learned knowledge from the existing model is transferred into the new learning task when training deep neural networks.
arXiv Detail & Related papers (2020-09-15T05:59:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.