中文
相关论文

相关论文: Don't be fooled: label leakage in explanation meth…

200 篇论文

Feature attribution methods help make machine learning-based inference explainable by determining how much one or several features have contributed to a model's output. A particularly popular attribution method is based on the Shapley value…

人工智能 · 计算机科学 2025-11-04 Filip Naudot , Tobias Sundqvist , Timotheus Kampik

In spite of increased attention on explainable machine learning models, explaining multi-output predictions has not yet been extensively addressed. Methods that use Shapley values to attribute feature contributions to the decision making…

机器学习 · 计算机科学 2023-03-31 Célia Wafa Ayad , Thomas Bonnier , Benjamin Bosch , Jesse Read

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

机器学习 · 计算机科学 2019-11-06 Mengjiao Yang , Been Kim

Multi-label classification is a type of classification task, it is used when there are two or more classes, and the data point we want to predict may belong to none of the classes or all of them at the same time. In the real world, many…

机器学习 · 计算机科学 2021-04-26 Shikun Chen

Transparency of Machine Learning models used for decision support in various industries becomes essential for ensuring their ethical use. To that end, feature attribution methods such as SHAP (SHapley Additive exPlanations) are widely used…

机器学习 · 计算机科学 2022-12-08 Anna Bogdanova , Akira Imakura , Tetsuya Sakurai , Tomoya Fujii , Teppei Sakamoto , Hiroyuki Abe

Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnostic local feature attribution method which uses the…

机器学习 · 计算机科学 2025-06-10 Mateusz Gajewski , Mikołaj Morzy , Adam Karczmarz , Piotr Sankowski

The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting models to downstream tasks. Instance attribution, one type of…

机器学习 · 计算机科学 2024-06-10 Jingtan Wang , Xiaoqiang Lin , Rui Qiao , Chuan-Sheng Foo , Bryan Kian Hsiang Low

While SHAP (SHapley Additive exPlanations) and other feature attribution methods are commonly employed to explain model predictions, their application within information retrieval (IR), particularly for complex outputs such as ranked lists,…

信息检索 · 计算机科学 2025-05-01 Maria Heuss , Maarten de Rijke , Avishek Anand

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Naman Bansal , Chirag Agarwal , Anh Nguyen

Many important questions about a model cannot be answered just by explaining how much each feature contributes to its output. To answer a broader set of questions, we generalize a popular, mathematically well-grounded explanation technique,…

机器学习 · 计算机科学 2020-06-16 Dillon Bowen , Lyle Ungar

Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails…

机器学习 · 计算机科学 2025-09-03 Woon Yee Ng , Li Rong Wang , Siyuan Liu , Xiuyi Fan

Local feature attribution methods are increasingly used to explain complex machine learning models. However, current methods are limited because they are extremely expensive to compute or are not capable of explaining a distributed series…

机器学习 · 计算机科学 2022-10-12 Hugh Chen , Scott M. Lundberg , Su-In Lee

Machine and deep learning have grown in popularity and use in biological research over the last decade but still present challenges in interpretability of the fitted model. The development and use of metrics to determine features driving…

Competitive methods for multi-label classification typically invest in learning labels together. To do so in a beneficial way, analysis of label dependence is often seen as a fundamental step, separate and prior to constructing a…

机器学习 · 统计学 2017-07-19 Jesse Read , Jaakko Hollmén

Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent…

机器学习 · 计算机科学 2024-05-14 Yuheng Jia , Jiawei Tang , Jiahao Jiang

With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especially the \textit{right to be forgotten} emphasized by…

密码学与安全 · 计算机科学 2026-04-10 Weidong Zheng , Kongyang Chen , Yao Huang , Yuanwei Guo , Yatie Xiao

Safe artificial intelligence for perception tasks remains a major challenge, partly due to the lack of data with high-quality labels. Annotations themselves are subject to aleatoric and epistemic uncertainty, which is typically ignored…

As an effective approach to quantify how training samples influence test sample, data attribution is crucial for understanding data and model and further enhance the transparency of machine learning models. We find that prevailing data…

机器学习 · 计算机科学 2025-08-08 Linxiao Yang , Xinyu Gu , Liang Sun

Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models, but it can be affected by the presence of ``informative'' labels, which occur when some classes are more likely to be labeled…

Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the…

机器学习 · 计算机科学 2021-06-01 Ramaravind Kommiya Mothilal , Divyat Mahajan , Chenhao Tan , Amit Sharma
‹ 上一页 1 2 3 10 下一页 ›