Efficient computation of contrastive explanations

Artelt, André; Hammer, Barbara

doi:10.1109/ijcnn52387.2021.9534454

Cited by 3 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [14] define a contrastive explanations consisting of two parts: a pertinent negative (counterfactual) and a pertinent positive. A pertinent positive [7,14,15] describes a minimal set of features that are already sufficient for the given prediction. As already mentioned, pertinent positives are usually considered as a part or addition of contrastive explanations and are assumed to provide additional insights why the model took a particular decision [14].…”

Section: Contrastive Explanationsmentioning

confidence: 99%

“…One could either require that all "turned on" features are equal to their original values in x orig or one could relax this and only require that they are close to their original values in x orig . The computation of a pertinent positive (also called sparsest pertinent positive) can be phrased as the following multi-objective optimization problem [7]:…”

Section: Contrastive Explanationsmentioning

confidence: 99%

“…a strict choice would be = 0. Since ( 3) is difficult to solve -a number of different methods for efficiently computing (approximate 7 ) pertinent positives have been proposed [7,14,15].…”

Section: Contrastive Explanationsmentioning

confidence: 99%

“…( 25) does not guarantee that x pp is the sparsest or closest pertinent positive of x orig under h (•) -it could happen that there exists an even sparser or closer pertinent positive of x orig under h (•) which was invalid under the old model h(•). However, it is guaranteed that x pp is a sparse pertinent positive of x orig under h (•) which we consider to be sufficient for practical purposes, in particular if taking into account the computational difficulties of computing a pertinent positive -as stated in [7], computing a pertinent positive (even of "classic" ML models) is not that easy.…”

Section: Modelingmentioning

confidence: 99%

“…The selection operator returns a vector, whereby it only selects a subset of indices from the original vector as specified in the set I 7. The approximation comes from giving up closeness -many methods successfully compute pertinent positives but can not guarantee that they are globally optimal.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Contrastive Explanations for Explaining Model Adaptations

Artelt¹,

Hinder²,

Vaquet³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Many decision making systems deployed in the real world are not static -a phenomenon known as model adaptation takes place over time. The need for transparency and interpretability of AI-based decision models is widely accepted and thus have been worked on extensively. Usually, explanation methods assume a static system that has to be explained. Explaining non-static systems is still an open research question, which poses the challenge how to explain model adaptations. In this contribution, we propose and (empirically) evaluate a framework for explaining model adaptations by contrastive explanations. We also propose a method for automatically finding regions in data space that are affected by a given model adaptation and thus should be explained.

show abstract

Section: Contrastive Explanationsmentioning

confidence: 99%

Section: Contrastive Explanationsmentioning

confidence: 99%

“…a strict choice would be = 0. Since ( 3) is difficult to solve -a number of different methods for efficiently computing (approximate 7 ) pertinent positives have been proposed [7,14,15].…”

Section: Contrastive Explanationsmentioning

confidence: 99%

Section: Modelingmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Contrastive Explanations for Explaining Model Adaptations

Artelt¹,

Hinder²,

Vaquet³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Contrasting Explanations for Understanding and Regularizing Model Adaptations

Artelt

Hinder

Vaquet

et al. 2022

Neural Process Lett

View full text Add to dashboard Cite

Many of today’s decision making systems deployed in the real world are not static—they are changing and adapting over time, a phenomenon known as model adaptation takes place. Because of their wide reaching influence and potentially serious consequences, the need for transparency and interpretability of AI-based decision making systems is widely accepted and thus have been worked on extensively—e.g. a very prominent class of explanations are contrasting explanations which try to mimic human explanations. However, usually, explanation methods assume a static system that has to be explained. Explaining non-static systems is still an open research question, which poses the challenge how to explain model differences, adaptations and changes. In this contribution, we propose and (empirically) evaluate a general framework for explaining model adaptations and differences by contrasting explanations. We also propose a method for automatically finding regions in data space that are affected by a given model adaptation—i.e. regions where the internal reasoning of the other (e.g. adapted) model changed—and thus should be explained. Finally, we also propose a regularization for model adaptations to ensure that the internal reasoning of the adapted model does not change in an unwanted way.

show abstract

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

Shrivastava

Kell

2021

Molecules

View full text Add to dashboard Cite

The question of molecular similarity is core in cheminformatics and is usually assessed via a pairwise comparison based on vectors of properties or molecular fingerprints. We recently exploited variational autoencoders to embed 6M molecules in a chemical space, such that their (Euclidean) distance within the latent space so formed could be assessed within the framework of the entire molecular set. However, the standard objective function used did not seek to manipulate the latent space so as to cluster the molecules based on any perceived similarity. Using a set of some 160,000 molecules of biological relevance, we here bring together three modern elements of deep learning to create a novel and disentangled latent space, viz transformers, contrastive learning, and an embedded autoencoder. The effective dimensionality of the latent space was varied such that clear separation of individual types of molecules could be observed within individual dimensions of the latent space. The capacity of the network was such that many dimensions were not populated at all. As before, we assessed the utility of the representation by comparing clozapine with its near neighbors, and we also did the same for various antibiotics related to flucloxacillin. Transformers, especially when as here coupled with contrastive learning, effectively provide one-shot learning and lead to a successful and disentangled representation of molecular latent spaces that at once uses the entire training set in their construction while allowing “similar” molecules to cluster together in an effective and interpretable way.

show abstract

Efficient computation of contrastive explanations

Cited by 3 publications

References 17 publications

Contrastive Explanations for Explaining Model Adaptations

Contrastive Explanations for Explaining Model Adaptations

Contrasting Explanations for Understanding and Regularizing Model Adaptations

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

Contact Info

Product

Resources

About