Results 311 to 320 of about 11,307,335 (373)

The Shapley Value in Database Management

SIGMOD record, 2023
Attribution scores can be applied in data management to quantify the contribution of individual items to conclusions from the data, as part of the explanation of what led to these conclusions.
L. Bertossi, B. Kimelfeld, Ester Livshits, Mikaël Monet   +3 more
semanticscholar   +1 more source

Modified Shapley Value-Based Profit Allocation Method for Wind Power Accommodation and Deep Peak Regulation of Thermal Power

IEEE transactions on industry applications, 2023
Peak regulation ancillary service plays a significant role in the safe and economic operation of power system with high wind energy penetration. However, the interest conflict in wind power accommodation and thermal power schedule results in insufficient
Wanli Wu, Jizhong Zhu, Yixi Chen, T. Luo, Puxin Shi, Wanshu Guo, P. Shi, Changming Jiang   +7 more
semanticscholar   +1 more source

Dynamic Shapley Value Computation

IEEE International Conference on Data Engineering, 2023
With the prevalence of data-driven research, data valuation has attracted attention from the computer science field. How to appraise a single datum becomes an imperative problem, especially in the context of machine learning. Shapley value is widely used
Jiayao Zhang, Haocheng Xia, Qiheng Sun, Jinfei Liu, Li Xiong, Jian Pei, Kui Ren   +6 more
semanticscholar   +1 more source

ShVEEGc: EEG Clustering With Improved Cosine Similarity-Transformed Shapley Value

IEEE Transactions on Emerging Topics in Computational Intelligence, 2023
As the number of unlabeled or mislabeled electroencephalogram (EEG) increases dramatically in such applications as cerebral disease diagnosis, rehabilitation, and brain-computer interfaces, the supervised approaches that require labels or markers become ...
Guanghui Li, Jiahua Shen, Chenglong Dai, Jia Wu, Stefanie I. Becker   +4 more
semanticscholar   +1 more source

Quantum Algorithms for Shapley Value Calculation

International Conference on Quantum Computing and Engineering, 2023
In the classical context, the cooperative game theory concept of the Shapley value has been adapted for post hoc explanations of Machine Learning (ML) models. However, this approach does not easily translate to eXplainable Quantum ML (XQML).
Iain Burge, Michel Barbeau, Joaquín García   +2 more
semanticscholar   +1 more source

GraphSVX: Shapley Value Explanations for Graph Neural Networks

ECML/PKDD, 2021
Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node representations, which renders their comprehension challenging. In this paper,
Alexandre Duval, Fragkiskos D. Malliaros
semanticscholar   +1 more source

Consistent Restricted Shapley Values

Mathematical Social Sciences, 1994
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Derks, J., Peters, H.
openaire   +1 more source

TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation

NLP4SCIENCE
As large language models (LLMs) become increasingly prevalent in critical applications, the need for interpretable AI has grown. We introduce TokenSHAP, a novel method for interpreting LLMs by attributing importance to individual tokens or substrings ...
Roni Goldshmidt, Miriam Horovicz
semanticscholar   +1 more source

Fast Shapley Value Computation in Data Assemblage Tasks as Cooperative Simple Games

Proc. ACM Manag. Data
In this paper, we tackle the challenging problem of Shapley value computation in data markets in a novel setting of data assemblage tasks with binary utility functions among data owners.
Xuan Luo, Jian Pei, Cheng Xu, Wenjie Zhang, Jianliang Xu   +4 more
semanticscholar   +1 more source

Provably Accurate Shapley Value Estimation via Leverage Score Sampling

International Conference on Learning Representations
Originally introduced in game theory, Shapley values have emerged as a central tool in explainable machine learning, where they are used to attribute model predictions to specific input features.
Christopher Musco, R. T. Witter
semanticscholar   +1 more source