paper-with-me

홈 › Papers

Towards trustable SHAP scores

2024-04-30 · Olivier Letoffe, Xuanxiang Huang, Joao Marques-Silva

SHAP scores represent the proposed use of the well-known Shapley values in eXplainable Artificial Intelligence (XAI). Recent work has shown that the exact computation of SHAP scores can produce unsatisfactory results. Concretely, for some ML models, SHAP scores will mislead with respect to relative feature influence. To address these limitations, recently proposed alternatives exploit different axiomatic aggregations, all of which are defined in terms of abductive explanations. However, the proposed axiomatic aggregations are not Shapley values. This paper investigates how SHAP scores can be modified so as to extend axiomatic aggregations to the case of Shapley values in XAI. More importantly, the proposed new definition of SHAP scores avoids all the known cases where unsatisfactory results have been identified. The paper also characterizes the complexity of computing the novel definition of SHAP scores, highlighting families of classifiers for which computing these scores is tractable. Furthermore, the paper proposes modifications to the existing implementations of SHAP scores. These modifications eliminate some of the known limitations of SHAP scores, and have negligible impact in terms of performance.

📄 PDF Abstract BibTeX arXiv:2405.00076

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Methods 이 논문이 사용한 방법론

SHAP 설명 없음
Characteristic Functions 설명 없음

Similar Papers 제목 키워드 기반

A Unified Analytical Framework for Trustable Machine Learning and Automation Running with Blockchain

2019-03-21 · Tao Wang

Traditional machine learning algorithms use data from databases that are mutable, and therefore the data cannot be fully trusted. Also, the machine learning process is difficult to automate. This paper proposes building …

BIG-bench Machine Learning

A Privacy-Preserving and Trustable Multi-agent Learning Framework

2021-06-02 · Anudit Nagar, Cuong Tran, Ferdinando Fioretto

Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has been shown that, even when data is not di…

Privacy Preserving

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

2024-09-30 · Luohe Shi, Yao Yao, Zuchao Li, Lefei Zhang 외

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs t…

Few-Shot LearningIn-Context Learningparameter-efficient fine-tuningQuestion Answering+2

ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification

2019-07-01 · ACL 2019 7 · Wei Jia, Dai Dai, Xinyan Xiao, Hua Wu

Distant supervision is widely used in relation classification in order to create large-scale training data by aligning a knowledge base with an unlabeled corpus. However, it also introduces amounts of noisy labels where …

ClassificationGeneral ClassificationRelationRelation Classification+1

Resilience of the Electric Grid through Trustable IoT-Coordinated Assets (Extended version)

2024-06-21 · Vineet J. Nair, Venkatesh Venkataramanan, Priyank Srivastava, Partha S. Sarker 외

The electricity grid has evolved from a physical system to a cyber-physical system with digital devices that perform measurement, control, communication, computation, and actuation. The increased penetration of distribut…