paper-with-me

홈 › Papers

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

2023-04-26 · Mingjie Li, Quanshi Zhang

In this technical note, we aim to explain a deep neural network (DNN) by quantifying the encoded interactions between input variables, which reflects the DNN's inference logic. Specifically, we first rethink the definition of interactions, and then formally define faithfulness and conciseness for interaction-based explanation. To this end, we propose two kinds of interactions, i.e., the AND interaction and the OR interaction. For faithfulness, we prove the uniqueness of the AND (OR) interaction in quantifying the effect of the AND (OR) relationship between input variables. Besides, based on AND-OR interactions, we design techniques to boost the conciseness of the explanation, while not hurting the faithfulness. In this way, the inference logic of a DNN can be faithfully and concisely explained by a set of symbolic concepts.

📄 PDF Abstract BibTeX arXiv:2304.13312

Code (1)

sjtu-xai-lab/interaction-concept pytorch

Similar Papers 제목 키워드 기반

Defining and Extracting generalizable interaction primitives from DNNs

2024-01-29 · Lu Chen, Siyu Lou, Benhao Huang, Quanshi Zhang

Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI. To this end, Ren et al. (2…

Defining and Learning Refined Temporal Relations in the Clinical Narrative

2020-11-01 · EMNLP (Louhi) 2020 11 · Kristin Wright-Bettner, Chen Lin, Timothy Miller, Steven Bethard 외

We present refinements over existing temporal relation annotations in the Electronic Medical Record clinical narrative. We refined the THYME corpus annotations to more faithfully represent nuanced temporality and nuanced…

Defining and Quantifying the Emergence of Sparse Concepts in DNNs

2021-11-11 · CVPR 2023 1 · Jie Ren, Mingjie Li, Qirui Chen, Huiqi Deng 외

This paper aims to illustrate the concept-emerging phenomenon in a trained DNN. Specifically, we find that the inference score of a DNN can be disentangled into the effects of a few interactive concepts. These concepts c…

NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding

2025-08-20 · Running Zhao, Zhihan Jiang, Xinchen Zhang, Chirui Chang 외 arxiv

Users often take notes for instructional videos to access key knowledge later without revisiting long videos. Automated note generation tools enable users to obtain informative notes efficiently. However, notes generated…

Technical Note: Game-Theoretic Interactions of Different Orders

2020-10-28 · Hao Zhang, Xu Cheng, Yiting Chen, Quanshi Zhang

In this study, we define interaction components of different orders between two input variables based on game theory. We further prove that interaction components of different orders satisfy several desirable properties.