An energy-based model for neuro-symbolic reasoning on knowledge graphs

被引:0
|
作者
Doldy, Dominik [1 ,2 ,3 ]
Garridoy, Josep Soler [1 ,2 ,4 ]
机构
[1] Siemens AG Technol, Siemens AI Lab, Munich, Germany
[2] Siemens AG, Munich, Germany
[3] European Space Agcy, Noordwijk, Netherlands
[4] European Commiss, Joint Res Ctr JRC, Seville, Spain
关键词
D O I
10.1109/ICMLA52953.2021.00151
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine learning on graph-structured data has recently become a major topic in industry and research, finding many exciting applications such as recommender systems and automated theorem proving. We propose an energy-based graph embedding algorithm to characterize industrial automation systems, integrating knowledge from different domains like industrial automation, communications and cybersecurity. By combining knowledge from multiple domains, the learned model is capable of making context-aware predictions regarding novel system events and can be used to evaluate the severity of anomalies that might be indicative of, e.g., cybersecurity breaches. The presented model is mappable to a biologically-inspired neural architecture, serving as a first bridge between graph embedding methods and neuromorphic computing - uncovering a promising edge application for this upcoming technology.
引用
收藏
页码:916 / 921
页数:6
相关论文
共 50 条
  • [1] Neuro-Symbolic Integration for Reasoning and Learning on Knowledge Graphs
    Werner, Luisa
    [J]. THIRTY-EIGTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 21, 2024, : 23429 - 23430
  • [2] Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs
    Chen, Shengyuan
    Cai, Yunfeng
    Fang, Huang
    Huang, Xiao
    Sun, Mingming
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [3] Neuro-symbolic representation learning on biological knowledge graphs
    Alshahrani, Mona
    Khan, Mohammad Asif
    Maddouri, Omar
    Kinjo, Akira R.
    Queralt-Rosinach, Nuria
    Hoehndorf, Robert
    [J]. BIOINFORMATICS, 2017, 33 (17) : 2723 - 2730
  • [4] Conversational Neuro-Symbolic Commonsense Reasoning
    Arabshahi, Forough
    Lee, Jennifer
    Gawarecki, Mikayla
    Mazaitis, Kathryn
    Azaria, Amos
    Mitchell, Tom
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4902 - 4911
  • [5] An Interpretable Neuro-symbolic Model for Raven’s Progressive Matrices Reasoning
    Shukuo Zhao
    Hongzhi You
    Ru-Yuan Zhang
    Bailu Si
    Zonglei Zhen
    Xiaohong Wan
    Da-Hui Wang
    [J]. Cognitive Computation, 2023, 15 : 1703 - 1724
  • [6] Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
    Amizadeh, Saeed
    Palangi, Hamid
    Polozov, Oleksandr
    Huang, Yichen
    Koishida, Kazuhito
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [7] An Interpretable Neuro-symbolic Model for Raven's Progressive Matrices Reasoning
    Zhao, Shukuo
    You, Hongzhi
    Zhang, Ru-Yuan
    Si, Bailu
    Zhen, Zonglei
    Wan, Xiaohong
    Wang, Da-Hui
    [J]. COGNITIVE COMPUTATION, 2023, 15 (05) : 1703 - 1724
  • [8] GNNQ: A Neuro-Symbolic Approach to Query Answering over Incomplete Knowledge Graphs
    Pflueger, Maximilian
    Cucala, David J. Tena
    Kostylev, Egor V.
    [J]. SEMANTIC WEB - ISWC 2022, 2022, 13489 : 481 - 497
  • [9] Improving the Integration of Neuro-Symbolic Rules with Case-Based Reasoning
    Prentzas, Jim
    Hatzilygeroudis, Ioannis
    Michail, Othon
    [J]. ARTIFICIAL INTELLIGENCE: THEORIES, MODELS AND APPLICATIONS, SETN 2008, 2008, 5138 : 377 - 382
  • [10] A probabilistic approximate logic for neuro-symbolic learning and reasoning
    Stehr, Mark-Oliver
    Kim, Minyoung
    Talcott, Carolyn L.
    [J]. JOURNAL OF LOGICAL AND ALGEBRAIC METHODS IN PROGRAMMING, 2022, 124