paper-with-me

홈 › Papers

Increasing Performance And Sample Efficiency With Model-agnostic Interactive Feature Attributions

2023-06-28 · Joran Michiels, Maarten De Vos, Johan Suykens

Model-agnostic feature attributions can provide local insights in complex ML models. If the explanation is correct, a domain expert can validate and trust the model's decision. However, if it contradicts the expert's knowledge, related work only corrects irrelevant features to improve the model. To allow for unlimited interaction, in this paper we provide model-agnostic implementations for two popular explanation methods (Occlusion and Shapley values) to enforce entirely different attributions in the complex model. For a particular set of samples, we use the corrected feature attributions to generate extra local data, which is used to retrain the model to have the right explanation for the samples. Through simulated and real data experiments on a variety of models we show how our proposed approach can significantly improve the model's performance only by augmenting its training dataset based on corrected explanations. Adding our interactive explanations to active learning settings increases the sample efficiency significantly and outperforms existing explanatory interactive strategies. Additionally we explore how a domain expert can provide feature attributions which are sufficiently correct to improve the model.

📄 PDF Abstract BibTeX arXiv:2306.16431

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms

2023-12-28 · Yichen Li, Chicheng Zhang

We study interactive imitation learning, where a learner interactively queries a demonstrating expert for action annotations, aiming to learn a policy that has performance competitive with the expert, using as few annota…

continuous-controlContinuous ControlImitation Learning

Learning versus Refutation in Noninteractive Local Differential Privacy

2022-10-26 · Alexander Edmonds, Aleksandar Nikolov, Toniann Pitassi

We study two basic statistical tasks in non-interactive local differential privacy (LDP): learning and refutation. Learning requires finding a concept that best fits an unknown target function (from labelled samples draw…

PAC learning

Improving Interactive Diagnostic Ability of a Large Language Model Agent Through Clinical Experience Learning

2025-02-24 · Zhoujian Sun, Ziyi Liu, Cheng Luo, Jiebin Chu 외

Recent advances in large language models (LLMs) have shown promising results in medical diagnosis, with some studies indicating superior performance compared to human physicians in specific scenarios. However, the diagno…

DiagnosticLanguage ModelingLanguage ModellingLarge Language Model+1

On the Power of Interactive Proofs for Learning

2024-04-11 · Tom Gur, Mohammad Mahdi Jahanara, Mohammad Mahdi Khodabandeh, Ninad Rajgopal 외

We continue the study of doubly-efficient proof systems for verifying agnostic PAC learning, for which we obtain the following results. - We construct an interactive protocol for learning the $t$ largest Fourier characte…

PAC learning

Interactive Segmentation and Report Generation for CT Images

2025-03-05 · Yannian Gu, Wenhui Lei, HanYu Chen, Xiaofan Zhang 외

Automated CT report generation plays a crucial role in improving diagnostic accuracy and clinical workflow efficiency. However, existing methods lack interpretability and impede patient-clinician understanding, while the…

AttributeDiagnosticInteractive SegmentationLesion Segmentation+1