Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs

26 April 2023

Papers citing "Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs"

10 / 10 papers shown

Title
Layerwise Change of Knowledge in Neural Networks Xu Cheng Lei Cheng Zhaoran Peng Yang Xu Tian Han Quanshi Zhang KELM FAtt 33 6 0 13 Sep 2024
Towards the Dynamics of a DNN Learning Symbolic Interactions Qihan Ren Yang Xu Junpeng Zhang Yue Xin Dongrui Liu Quanshi Zhang 26 7 0 27 Jul 2024
Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs Siyu Lou Yuntian Chen Xiaodan Liang Liang Lin Quanshi Zhang 32 2 0 20 May 2024
Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features Junpeng Zhang Qing Li Liang Lin Quanshi Zhang AI4CE 35 5 0 16 May 2024
Defining and Extracting generalizable interaction primitives from DNNs Lu Chen Siyu Lou Benhao Huang Quanshi Zhang 26 9 0 29 Jan 2024
Towards Attributions of Input Variables in a Coalition Xinhao Zheng Huiqi Deng Bo Fan Quanshi Zhang 22 1 0 23 Sep 2023
Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models Qihan Ren Maximilian Brunner Wen Shen S. Mintchev 34 11 0 03 May 2023
Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions Huiqi Deng Na Zou Mengnan Du Weifu Chen Guo-Can Feng Ziwei Yang Zheyang Li Quanshi Zhang FAtt TDI 49 22 0 02 Mar 2023
Does a Neural Network Really Encode Symbolic Concepts? Mingjie Li Quanshi Zhang 21 30 0 25 Feb 2023
Discovering and Explaining the Representation Bottleneck of DNNs Huiqi Deng Qihan Ren Hao Zhang Quanshi Zhang 37 59 0 11 Nov 2021