paper-with-me

Papers

Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff

2021-07-12 · Mitchell Naylor, Christi French, Samantha Terker, Uday Kamath

The healthcare domain is one of the most exciting application areas for machine learning, but a lack of model transparency contributes to a lag in adoption within the industry. In this work, we explore the current art of explainability and interpretability within a case study in clinical text classification, using a task of mortality prediction within MIMIC-III clinical notes. We demonstrate various visualization techniques for fully interpretable methods as well as model-agnostic post hoc attributions, and we provide a generalized method for evaluating the quality of explanations using infidelity and local Lipschitz across model types from logistic regression to BERT variants. With these metrics, we introduce a framework through which practitioners and researchers can assess the frontier between a model's predictive performance and the quality of its available explanations. We make our code available to encourage continued refinement of these methods.

📄 PDF Abstract BibTeX arXiv:2107.05693

Code (1)

mnaylor5/quantifying-explainability 공식 구현 pytorch

Tasks

Mortality Predictiontext-classificationText Classification

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…
SHAP 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

Mining Potentially Explanatory Patterns via Partial Solutions

2024-04-05 · GianCarlo Catalano, Alexander E. I. Brownlee, David Cairns, John McCall 외

Genetic Algorithms have established their capability for solving many complex optimization problems. Even as good solutions are produced, the user's understanding of a problem is not necessarily improved, which can lead …

Combinatorial Optimization

Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models

2022-06-08 · NAACL (TrustNLP) 2022 7 · Esma Balkir, Svetlana Kiritchenko, Isar Nejadgholi, Kathleen C. Fraser

Motivations for methods in explainable artificial intelligence (XAI) often include detecting, quantifying and mitigating bias, and contributing to making machine learning models fairer. However, exactly how an XAI method…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Fairness

Quantifying Explainable AI-introduced signal noise on ECG data with Spectral Entropy

2026-06-23 · David A. Kelly, Nathan Blake arxiv

Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be trusted and decisions justified. Explainability (XAI) tools use heur…

Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms

2019-10-16 · Zhong Qiu Lin, Mohammad Javad Shafiee, Stanislav Bochkarev, Michael St. Jules 외

There has been a significant surge of interest recently around the concept of explainable artificial intelligence (XAI), where the goal is to produce an interpretation for a decision made by a machine learning algorithm.…

Decision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)image-classification+1

Stop ordering machine learning algorithms by their explainability! A user-centered investigation of performance and explainability

2022-06-20 · Lukas-Valentin Herm, Kai Heinrich, Jonas Wanner, Christian Janiesch

Machine learning algorithms enable advanced decision making in contemporary intelligent systems. Research indicates that there is a tradeoff between their model performance and explainability. Machine learning models wit…

BIG-bench Machine LearningDecision MakingExplainable artificial intelligence