收藏切换
Abductive Learning Method with Rejection Reasoning
收藏切换
Yuxuan Huang, Yuan Jiang*
Journal of Computer Research and Development | 2024, 61(7) : 1791 - 1798
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(7): 1791-1798
• Artificial Intelligence •
Abductive Learning Method with Rejection Reasoning
Full
Yuxuan Huang, Yuan Jiang*
Affiliations
  • National Key Laboratory for Novel Software Technology (Nanjing University), Nanjing 210023
  • born in 1996. PhD. His main research interests include abductive learning, knowledge and data dual-driven learning, and machine learning

    born in 1976. PhD, professor, PhD supervisor. Her main research interests include artificial intelligence, machine learning and data mining

About Author:

born in 1996. PhD. His main research interests include abductive learning, knowledge and data dual-driven learning, and machine learning

born in 1976. PhD, professor, PhD supervisor. Her main research interests include artificial intelligence, machine learning and data mining

Published: 2024-07-01 doi: 10.7544/issn1000-1239.202330547
Outline
收藏切换

In recent years, many research efforts have focused on combining data-driven machine learning with knowledge-driven logical reasoning, aiming to improve the performance of machine learning systems. Many works have attempted to use abductive reasoning to integrate machine learning and logical reasoning into a unified framework. These methods typically first generate pseudo-labels through machine learning models, and then use abductive reasoning to revise the inconsistent pseudo-labels, which serves to update the machine learning model and the above routine repeats. However, there may be incorrect labels in the abduced labels, which could have a negative impact on the training of the machine learning model and are challenging to detect. We propose abductive learning with rejection reasoning, a method that takes into account both model uncertainty and reasoning uncertainty of the abduced labels. This strategy comprehensively evaluates the reliability of abductive results from the perspective of both the data and knowledge levels, and avoids the negative impact of unreliable abduced labels on model training by rejecting some of the abductive reasoning results. Empirical studies show that the proposed method can reduce the proportion of incorrect abduced labels. In turn, this facilitates a faster training process for abductive learning and improves its overall performance.

abductive learning  /  machine learning  /  logical reasoning  /  abductive reasoning  /  neuro-symbolic learning
黄宇轩, 姜远. 带拒绝推理的反绎学习方法. 计算机研究与发展, 2024 , 61 (7) : 1791 -1798 . DOI: 10.7544/issn1000-1239.202330547
Yuxuan Huang, Yuan Jiang. Abductive Learning Method with Rejection Reasoning[J]. Journal of Computer Research and Development, 2024 , 61 (7) : 1791 -1798 . DOI: 10.7544/issn1000-1239.202330547
Year 2024 volume 61 Issue 7
84
41
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202330547
  • Receive Date:2023-06-24
  • Online Date:2026-11-17
  • Published:2024-07-01
Article Data
Affiliations
History
  • Received:2023-06-24
  • Revised:2023-11-06
Affiliations
    National Key Laboratory for Novel Software Technology (Nanjing University), Nanjing 210023
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330547
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT