paper-with-me

홈 › Papers

Semantic Explanations of Predictions

2018-05-27 · Freddy Lecue, Jiewen Wu

The main objective of explanations is to transmit knowledge to humans. This work proposes to construct informative explanations for predictions made from machine learning models. Motivated by the observations from social sciences, our approach selects data points from the training sample that exhibit special characteristics crucial for explanation, for instance, ones contrastive to the classification prediction and ones representative of the models. Subsequently, semantic concepts are derived from the selected data points through the use of domain ontologies. These concepts are filtered and ranked to produce informative explanations that improves human understanding. The main features of our approach are that (1) knowledge about explanations is captured in the form of ontological concepts, (2) explanations include contrastive evidences in addition to normal evidences, and (3) explanations are user relevant.

📄 PDF Abstract BibTeX arXiv:1805.10587

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance

2023-07-14 · Omer Reingold, Judy Hanwen Shen, Aditi Talati

While explainability is a desirable characteristic of increasingly complex black-box models, modern explanation methods have been shown to be inconsistent and contradictory. The semantics of explanations is not always fu…

model

Grid Saliency for Context Explanations of Semantic Segmentation

2019-07-30 · NeurIPS 2019 12 · Lukas Hoyer, Mauricio Munoz, Prateek Katiyar, Anna Khoreva 외

Recently, there has been a growing interest in developing saliency methods that provide visual explanations of network predictions. Still, the usability of existing methods is limited to image classification models. To o…

image-classificationImage ClassificationSegmentationSemantic Segmentation

Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-making

2022-06-17 · Charles Wan, Rodrigo Belo, Leid Zejnilović

Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task wit…

Decision Making

Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability

2022-07-20 · CVPR 2023 1 · Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate mode…

Structure Your Data: Towards Semantic Graph Counterfactuals

2024-03-11 · Angeliki Dimitriou, Maria Lymperaiou, Giorgos Filandrianos, Konstantinos Thomas 외

Counterfactual explanations (CEs) based on concepts are explanations that consider alternative scenarios to understand which high-level semantic features contributed to particular model predictions. In this work, we prop…

counterfactualDescriptiveGraph Similarity