Computer Science > Machine Learning
[Submitted on 3 Sep 2021 (v1), last revised 21 Feb 2023 (this version, v6)]
Title:Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation
View PDFAbstract:Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans. However, their most significant drawback is the lack of interpretability, which makes them less attractive in many real-world applications. When relating to the moral problem or the environmental factors that are uncertain such as crime judgment, financial analysis, and medical diagnosis, it is essential to mine the evidence for the model's prediction (interpret model knowledge) to convince humans. Thus, investigating how to interpret model knowledge is of paramount importance for both academic research and real applications.
Submission history
From: Jiahui Li [view email][v1] Fri, 3 Sep 2021 08:34:37 UTC (6,325 KB)
[v2] Mon, 4 Oct 2021 05:46:35 UTC (6,325 KB)
[v3] Tue, 5 Oct 2021 05:00:35 UTC (6,325 KB)
[v4] Thu, 28 Jul 2022 10:42:16 UTC (6,325 KB)
[v5] Sat, 20 Aug 2022 01:52:05 UTC (6,325 KB)
[v6] Tue, 21 Feb 2023 16:33:57 UTC (6,325 KB)
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
IArxiv Recommender
(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.