Insights into Data through Model Behaviour: An Explainability-driven
Strategy for Data Auditing for Responsible Computer Vision Applications
- URL: http://arxiv.org/abs/2106.09177v1
- Date: Wed, 16 Jun 2021 23:46:39 GMT
- Title: Insights into Data through Model Behaviour: An Explainability-driven
Strategy for Data Auditing for Responsible Computer Vision Applications
- Authors: Alexander Wong, Adam Dorfman, Paul McInnis, and Hayden Gunraj
- Abstract summary: This study explores an explainability-driven strategy to data auditing.
We demonstrate this strategy by auditing two popular medical benchmark datasets.
We discover hidden data quality issues that lead deep learning models to make predictions for the wrong reasons.
- Score: 70.92379567261304
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this study, we take a departure and explore an explainability-driven
strategy to data auditing, where actionable insights into the data at hand are
discovered through the eyes of quantitative explainability on the behaviour of
a dummy model prototype when exposed to data. We demonstrate this strategy by
auditing two popular medical benchmark datasets, and discover hidden data
quality issues that lead deep learning models to make predictions for the wrong
reasons. The actionable insights gained from this explainability driven data
auditing strategy is then leveraged to address the discovered issues to enable
the creation of high-performing deep learning models with appropriate
prediction behaviour. The hope is that such an explainability-driven strategy
can be complimentary to data-driven strategies to facilitate for more
responsible development of machine learning algorithms for computer vision
applications.
Related papers
- DISCOVER: A Data-driven Interactive System for Comprehensive Observation, Visualization, and ExploRation of Human Behaviour [6.716560115378451]
We introduce a modular, flexible, yet user-friendly software framework specifically developed to streamline computational-driven data exploration for human behavior analysis.
Our primary objective is to democratize access to advanced computational methodologies, thereby enabling researchers across disciplines to engage in detailed behavioral analysis without the need for extensive technical proficiency.
arXiv Detail & Related papers (2024-07-18T11:28:52Z) - Advancing continual lifelong learning in neural information retrieval: definition, dataset, framework, and empirical evaluation [3.2340528215722553]
A systematic task formulation of continual neural information retrieval is presented.
A comprehensive continual neural information retrieval framework is proposed.
Empirical evaluations illustrate that the proposed framework can successfully prevent catastrophic forgetting in neural information retrieval.
arXiv Detail & Related papers (2023-08-16T14:01:25Z) - 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) - Predicting Seriousness of Injury in a Traffic Accident: A New Imbalanced
Dataset and Benchmark [62.997667081978825]
The paper introduces a new dataset to assess the performance of machine learning algorithms in the prediction of the seriousness of injury in a traffic accident.
The dataset is created by aggregating publicly available datasets from the UK Department for Transport.
arXiv Detail & Related papers (2022-05-20T21:15:26Z) - Leveraging Adversarial Examples to Quantify Membership Information
Leakage [30.55736840515317]
We develop a novel approach to address the problem of membership inference in pattern recognition models.
We argue that this quantity reflects the likelihood of belonging to the training data.
Our method performs comparable or even outperforms state-of-the-art strategies.
arXiv Detail & Related papers (2022-03-17T19:09:38Z) - Representations of epistemic uncertainty and awareness in data-driven
strategies [0.0]
We present a theoretical model for uncertainty in knowledge representation and its transfer mediated by agents.
We look at inequivalent knowledge representations in terms of inferences, preference relations, and information measures.
We discuss some implications of the proposed model for data-driven strategies.
arXiv Detail & Related papers (2021-10-21T21:18:21Z) - Knowledge-driven Active Learning [70.37119719069499]
Active learning strategies aim at minimizing the amount of labelled data required to train a Deep Learning model.
Most active strategies are based on uncertain sample selection, and even often restricted to samples lying close to the decision boundary.
Here we propose to take into consideration common domain-knowledge and enable non-expert users to train a model with fewer samples.
arXiv Detail & Related papers (2021-10-15T06:11:53Z) - 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) - Explainable Adversarial Attacks in Deep Neural Networks Using Activation
Profiles [69.9674326582747]
This paper presents a visual framework to investigate neural network models subjected to adversarial examples.
We show how observing these elements can quickly pinpoint exploited areas in a model.
arXiv Detail & Related papers (2021-03-18T13:04:21Z)
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.