XAI for Transformers: Better Explanations through Conservative Propagation

Ameen, Ali; Schnake, Thomas; Eberle, Oliver; Montavon, Grégoire; Müller, Klaus‐Robert; Wolf, Lior

doi:10.48550/arxiv.2202.07304

Cited by 3 publications

(2 citation statements)

References 30 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are based on a per-class weighted linear sum of visual patterns present at various spatial locations in an image and produce heatmaps representations that indicate which regions of the input image were most important for CNN’s decisions. Recently, there are initial attempts to use Grad-CAM on transformer architectures but their effectiveness is still on debate [ 46 , 47 ]. However, thanks to the attention mechanism, transformers are intrinsically able to support explanations based on the inspection of the weights in the attention matrices, like the Attention Rollout [ 48 ].…”

Section: Discussionmentioning

confidence: 99%

Convolutional Networks and Transformers for Mammography Classification: An Experimental Study

Cantone

Marrocco

Tortorella

et al. 2023

Sensors

View full text Add to dashboard Cite

Convolutional Neural Networks (CNN) have received a large share of research in mammography image analysis due to their capability of extracting hierarchical features directly from raw data. Recently, Vision Transformers are emerging as viable alternative to CNNs in medical imaging, in some cases performing on par or better than their convolutional counterparts. In this work, we conduct an extensive experimental study to compare the most recent CNN and Vision Transformer architectures for whole mammograms classification. We selected, trained and tested 33 different models, 19 convolutional- and 14 transformer-based, on the largest publicly available mammography image database OMI-DB. We also performed an analysis of the performance at eight different image resolutions and considering all the individual lesion categories in isolation (masses, calcifications, focal asymmetries, architectural distortions). Our findings confirm the potential of visual transformers, which performed on par with traditional CNNs like ResNet, but at the same time show a superiority of modern convolutional networks like EfficientNet.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional Networks and Transformers for Mammography Classification: An Experimental Study

Cantone

Marrocco

Tortorella

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In Kokalj et al (2021), the known feature importance XAI approach 'shapley additive explanations' (Lundberg & Lee, 2017) has been adapted to account for the contextualized (token-based) text representation in language models. Further, approaches based on the attention weights in language models have been recently proposed (Ali et al, 2022;S. Liu et al, 2021), similarly establishing feature importance scores for language model predictions.…”

Section: Ad Category B)mentioning

confidence: 99%

Global reconstruction of language models with linguistic rules – Explainable AI for online consumer reviews

et al. 2022

View full text Add to dashboard Cite

Analyzing textual data by means of AI models has been recognized as highly relevant in information systems research and practice, since a vast amount of data on eCommerce platforms, review portals or social media is given in textual form. Here, language models such as BERT, which are deep learning AI models, constitute a breakthrough and achieve leading-edge results in many applications of text analytics such as sentiment analysis in online consumer reviews. However, these language models are “black boxes”: It is unclear how they arrive at their predictions. Yet, applications of language models, for instance, in eCommerce require checks and justifications by means of global reconstruction of their predictions, since the decisions based thereon can have large impacts or are even mandatory due to regulations such as the GDPR. To this end, we propose a novel XAI approach for global reconstructions of language model predictions for token-level classifications (e.g., aspect term detection) by means of linguistic rules based on NLP building blocks (e.g., part-of-speech). The approach is analyzed on different datasets of online consumer reviews and NLP tasks. Since our approach allows for different setups, we further are the first to analyze the trade-off between comprehensibility and fidelity of global reconstructions of language model predictions. With respect to this trade-off, we find that our approach indeed allows for balanced setups for global reconstructions of BERT’s predictions. Thus, our approach paves the way for a thorough understanding of language model predictions in text analytics. In practice, our approach can assist businesses in their decision-making and supports compliance with regulatory requirements.

show abstract

Transformer models in biomedicine

Madan,

Lentzen,

Brandt

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Deep neural networks (DNN) have fundamentally revolutionized the artificial intelligence (AI) field. The transformer model is a type of DNN that was originally used for the natural language processing tasks and has since gained more and more attention for processing various kinds of sequential data, including biological sequences and structured electronic health records. Along with this development, transformer-based models such as BioBERT, MedBERT, and MassGenie have been trained and deployed by researchers to answer various scientific questions originating in the biomedical domain. In this paper, we review the development and application of transformer models for analyzing various biomedical-related datasets such as biomedical textual data, protein sequences, medical structured-longitudinal data, and biomedical images as well as graphs. Also, we look at explainable AI strategies that help to comprehend the predictions of transformer-based models. Finally, we discuss the limitations and challenges of current models, and point out emerging novel research directions.

show abstract

XAI for Transformers: Better Explanations through Conservative Propagation

Cited by 3 publications

References 30 publications

Convolutional Networks and Transformers for Mammography Classification: An Experimental Study

Convolutional Networks and Transformers for Mammography Classification: An Experimental Study

Global reconstruction of language models with linguistic rules – Explainable AI for online consumer reviews

Transformer models in biomedicine

Contact Info

Product

Resources

About