TY - GEN
T1 - MMCIE
T2 - 31st International Conference on Neural Information Processing, ICONIP 2024
AU - Huang, Mingfeng
AU - Huang, Guoheng
AU - Zhou, Xiaomin
AU - Pun, Chi Man
AU - Chen, Xuhang
AU - Yuan, Xiaochen
AU - Zhong, Guo
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - Shapley values are extensively utilized in Explainable Artificial Intelligence to interpret predictions made by complex machine learning models. However, much of the research has focused on addressing the costly computational aspects of Shapley values, neglecting the rich interactive knowledge representation inherent in the data within the model. Therefore, MMCIE is proposed in this article, focusing on exploring the conceptual modeling of data by the model. Based on Shapley values, it defines the interaction between inner and outer coalitions to accurately quantify the concept of model modeling. Specifically, the Superpixel Coalitions Selecting Module (SCSM) is proposed, which defines coalitions as entities and paves the way for calculating multivariable interaction values and internal interaction values. Additionally, the Internal and External Interaction Module (IEIM) acts as a bridge, computing and connecting the internal and external interaction values of coalitions, thereby constructing the feature prototype of the model. Moreover, the Multi-order Equidistance Coalitions Modeling Module (MECMM) is introduced as an effective approach to reduce computational complexity and explore the storage methods of the model’s conceptual modeling. Experiments on two datasets show the advantage of MMCIE over existing methods, revealing the model’s concept modeling process through multi-order interactions and offering a fresh view for model interpretation.
AB - Shapley values are extensively utilized in Explainable Artificial Intelligence to interpret predictions made by complex machine learning models. However, much of the research has focused on addressing the costly computational aspects of Shapley values, neglecting the rich interactive knowledge representation inherent in the data within the model. Therefore, MMCIE is proposed in this article, focusing on exploring the conceptual modeling of data by the model. Based on Shapley values, it defines the interaction between inner and outer coalitions to accurately quantify the concept of model modeling. Specifically, the Superpixel Coalitions Selecting Module (SCSM) is proposed, which defines coalitions as entities and paves the way for calculating multivariable interaction values and internal interaction values. Additionally, the Internal and External Interaction Module (IEIM) acts as a bridge, computing and connecting the internal and external interaction values of coalitions, thereby constructing the feature prototype of the model. Moreover, the Multi-order Equidistance Coalitions Modeling Module (MECMM) is introduced as an effective approach to reduce computational complexity and explore the storage methods of the model’s conceptual modeling. Experiments on two datasets show the advantage of MMCIE over existing methods, revealing the model’s concept modeling process through multi-order interactions and offering a fresh view for model interpretation.
KW - Feature Attribution Methods
KW - Shapley Values
KW - XAI
UR - https://www.scopus.com/pages/publications/105009918316
U2 - 10.1007/978-981-96-6948-6_1
DO - 10.1007/978-981-96-6948-6_1
M3 - Conference contribution
AN - SCOPUS:105009918316
SN - 9789819669479
T3 - Communications in Computer and Information Science
SP - 1
EP - 15
BT - Neural Information Processing - 31st International Conference, ICONIP 2024, Proceedings
A2 - Mahmud, Mufti
A2 - Doborjeh, Maryam
A2 - Wong, Kevin
A2 - Leung, Andrew Chi Sing
A2 - Doborjeh, Zohreh
A2 - Tanveer, M.
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 2 December 2024 through 6 December 2024
ER -