Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation-Reference-Cited by-同舟云学术

Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation

Published:2021-10-17 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 29th ACM International Conference on Multimedia
language:
Short-container-title:

Author:

Li Jiahui¹,Kuang Kun¹,Li Lin¹,Chen Long²,Zhang Songyang³,Shao Jian¹,Xiao Jun¹

Affiliation:

1. Zhejiang University, Hangzhou, China

2. Columbia University, Manhattan, NY, USA

3. University of Rochester, Rochester, NY, USA

Funder

the National Key Research and Development Project of China

the Fundamental Research Funds for the Central Universities

Zhejiang Province Natural Science Foundation

he National Natural Science Foundation of China

Key R & D Projects of the Ministry of Science and Technology

Zhejiang Innovation Foundation

Zhejiang Natural Science Foundation

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3474085.3475337

Reference48 articles.

1. Marco Ancona Cengiz Oztireli and Markus Gross. 2019. Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation. In ICML. Marco Ancona Cengiz Oztireli and Markus Gross. 2019. Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation. In ICML.

2. Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers

3. Philippe Bracke Anupam Datta Carsten Jung and Shayak Sen. 2019. Machine learning explainability in finance: an application to default risk analysis. (2019). Philippe Bracke Anupam Datta Carsten Jung and Shayak Sen. 2019. Machine learning explainability in finance: an application to default risk analysis. (2019).

Cited by 9 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. What Does a Model Really Look at?: Extracting Model-Oriented Concepts for Explaining Deep Neural Networks;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-07

2. ESC: Explaining the Predictions of Deep Neural Networks via Concept Similarity;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

3. Improving the Explain-Any-Concept by Introducing Nonlinearity to the Trainable Surrogate Model;2024 32nd Signal Processing and Communications Applications Conference (SIU);2024-05-15

4. Shapley Value Guided Extractive Text Summarization;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Explainable Machine Learning for Credit Risk Management When Features are Dependent;Measurement: Interdisciplinary Research and Perspectives;2024-03