Benchmark data to study the influence of pre-training on explanation
performance in MR image classification
- URL: http://arxiv.org/abs/2306.12150v1
- Date: Wed, 21 Jun 2023 09:53:37 GMT
- Title: Benchmark data to study the influence of pre-training on explanation
performance in MR image classification
- Authors: Marta Oliveira, Rick Wilming, Benedict Clark, C\'eline Budding, Fabian
Eitel, Kerstin Ritter, Stefan Haufe
- Abstract summary: CNNs are frequently and successfully used in medical prediction tasks.
They are often used in combination with transfer learning, leading to improved performance when training data for the task are scarce.
Previous studies have rarely quantitatively evaluated the 'explanation performance' of XAI methods against ground-truth data.
- Score: 0.6927055673104934
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Convolutional Neural Networks (CNNs) are frequently and successfully used in
medical prediction tasks. They are often used in combination with transfer
learning, leading to improved performance when training data for the task are
scarce. The resulting models are highly complex and typically do not provide
any insight into their predictive mechanisms, motivating the field of
'explainable' artificial intelligence (XAI). However, previous studies have
rarely quantitatively evaluated the 'explanation performance' of XAI methods
against ground-truth data, and transfer learning and its influence on objective
measures of explanation performance has not been investigated. Here, we propose
a benchmark dataset that allows for quantifying explanation performance in a
realistic magnetic resonance imaging (MRI) classification task. We employ this
benchmark to understand the influence of transfer learning on the quality of
explanations. Experimental results show that popular XAI methods applied to the
same underlying model differ vastly in performance, even when considering only
correctly classified examples. We further observe that explanation performance
strongly depends on the task used for pre-training and the number of CNN layers
pre-trained. These results hold after correcting for a substantial correlation
between explanation and classification performance.
Related papers
- Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance.
Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning.
Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
arXiv Detail & Related papers (2024-08-08T17:20:08Z) - Improvement of Applicability in Student Performance Prediction Based on Transfer Learning [2.3290007848431955]
This study proposes a method to improve prediction accuracy by employing transfer learning techniques on the dataset with varying distributions.
The model was trained and evaluated to enhance its generalization ability and prediction accuracy.
Experiments demonstrated that this approach excels in reducing Root Mean Square Error (RMSE) and Mean Absolute Error (MAE)
The results demonstrate that freezing more layers improves performance for complex and noisy data, whereas freezing fewer layers is more effective for simpler and larger datasets.
arXiv Detail & Related papers (2024-06-01T13:09:05Z) - Learning with Noisy Foundation Models [95.50968225050012]
This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.
We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
arXiv Detail & Related papers (2024-03-11T16:22:41Z) - Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation [53.27596811146316]
Diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts.
We present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep.
We introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest.
arXiv Detail & Related papers (2024-01-17T07:58:18Z) - Uplift Modeling based on Graph Neural Network Combined with Causal
Knowledge [9.005051998738134]
We propose a framework based on graph neural networks that combine causal knowledge with an estimate of uplift value.
Our findings demonstrate that this method works effectively for predicting uplift values, with small errors in typical simulated data.
arXiv Detail & Related papers (2023-11-14T07:21:00Z) - Understanding and Mitigating the Label Noise in Pre-training on
Downstream Tasks [91.15120211190519]
This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks.
We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
arXiv Detail & Related papers (2023-09-29T06:18:15Z) - Data-Centric Machine Learning in the Legal Domain [0.2624902795082451]
This paper explores how changes in a data set influence the measured performance of a model.
Using three publicly available data sets from the legal domain, we investigate how changes to their size, the train/test splits, and the human labelling accuracy impact the performance.
The observed effects are surprisingly pronounced, especially when the per-class performance is considered.
arXiv Detail & Related papers (2022-01-17T23:05:14Z) - Efficient Estimation of Influence of a Training Instance [56.29080605123304]
We propose an efficient method for estimating the influence of a training instance on a neural network model.
Our method is inspired by dropout, which zero-masks a sub-network and prevents the sub-network from learning each training instance.
We demonstrate that the proposed method can capture training influences, enhance the interpretability of error predictions, and cleanse the training dataset for improving generalization.
arXiv Detail & Related papers (2020-12-08T04:31:38Z) - Using Cross-Loss Influence Functions to Explain Deep Network
Representations [1.7778609937758327]
We show that influence functions can be extended to handle mismatched training and testing settings.
Our result enables us to compute the influence of unsupervised and self-supervised training examples with respect to a supervised test objective.
arXiv Detail & Related papers (2020-12-03T03:43:26Z) - Influence Functions in Deep Learning Are Fragile [52.31375893260445]
influence functions approximate the effect of samples in test-time predictions.
influence estimates are fairly accurate for shallow networks.
Hessian regularization is important to get highquality influence estimates.
arXiv Detail & Related papers (2020-06-25T18:25:59Z)
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.