Zobrazeno 1 - 10
of 1 001
pro vyhledávání: '"Bui, Ngoc"'
Autor:
Zhang, Jiasheng, Chen, Jialin, Maatouk, Ali, Bui, Ngoc, Xie, Qianqian, Tassiulas, Leandros, Shao, Jie, Xu, Hua, Ying, Rex
With the advent of large language models (LLMs), managing scientific literature via LLMs has become a promising direction of research. However, existing approaches often overlook the rich structural and semantic relevance among scientific literature,
Externí odkaz:
http://arxiv.org/abs/2409.12177
The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based explainability app
Externí odkaz:
http://arxiv.org/abs/2405.14352
Algorithmic recourse emerges as a prominent technique to promote the explainability, transparency and hence ethics of machine learning models. Existing algorithmic recourse approaches often assume an invariant predictive model; however, the predictiv
Externí odkaz:
http://arxiv.org/abs/2311.11349
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-23 (2024)
Abstract It is well known that the roughness of a wall plays a crucial role in determining the passive earth pressure that is exerted on a rigid wall. While the effects of positive wall roughness have been extensively studied in the past few decades,
Externí odkaz:
https://doaj.org/article/7b8b37bb682e4fcba33c03e65f41bdc1
Explaining algorithmic decisions and recommending actionable feedback is increasingly important for machine learning applications. Recently, significant efforts have been invested in finding a diverse set of recourses to cover the wide spectrum of us
Externí odkaz:
http://arxiv.org/abs/2302.11213
A recourse action aims to explain a particular algorithmic decision by showing one specific way in which the instance could be modified to receive an alternate outcome. Existing recourse generation methods often assume that the machine learning model
Externí odkaz:
http://arxiv.org/abs/2302.11211
Publikováno v:
Asian Review of Accounting, 2023, Vol. 32, Issue 2, pp. 349-369.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/ARA-03-2023-0073