paper-with-me

Papers

Missingness Bias Calibration in Feature Attribution Explanations

2026-03-05 · Shailesh Sridhar, Anton Xue, Eric Wong arxiv

Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out-of-distribution inputs. Existing solutions treat this as a deep representational flaw that requires expensive retraining or architectural modifications. In this work, we challenge this assumption and show that missingness bias can be effectively treated as a superficial artifact of the model's output space. We introduce MCal, a lightweight post-hoc method that corrects this bias by fine-tuning a simple linear head on the outputs of a frozen base model. Surprisingly, we find this simple correction consistently reduces missingness bias and is competitive with, or even outperforms, prior heavyweight approaches across diverse medical benchmarks spanning vision, language, and tabular domains.

📄 PDF Abstract BibTeX arXiv:2603.04831

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance

Similar Papers 제목 키워드 기반

Calibration Meets Explanation: A Simple and Effective Approach for Model Confidence Estimates

2022-11-06 · Dongfang Li, Baotian Hu, Qingcai Chen

Calibration strengthens the trustworthiness of black-box models by producing better accurate confidence estimates on given examples. However, little is known about if model explanations can help confidence calibration. I…

Explanation Bias is a Product: Revealing the Hidden Lexical and Position Preferences in Post-Hoc Feature Attribution

2025-12-11 · Jonathan Kamp, Roos Bakker, Dominique Blok arxiv

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. Howeve…

Learning Deep Attribution Priors Based On Prior Knowledge

2019-12-20 · NeurIPS 2020 12 · Ethan Weinberger, Joseph Janizek, Su-In Lee

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. H…

Feature Importance

Feature Attributions and Counterfactual Explanations Can Be Manipulated

2021-06-23 · Dylan Slack, Sophie Hilgard, Sameer Singh, Himabindu Lakkaraju

As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explain model predictions. Such \textit{explan…

BIG-bench Machine LearningcounterfactualDecision Making

Bias Also Matters: Bias Attribution for Deep Neural Network Explanation

2019-05-01 · ICLR 2019 5 · Shengjie Wang, Tianyi Zhou, Jeff Bilmes

The gradient of a deep neural network (DNN) w.r.t. the input provides information that can be used to explain the output prediction in terms of the input features and has been widely studied to assist in interpreting DNN…

Attribute