RL2: A Call for Simultaneous Representation Learning and Rule Learning for Graph Streams
RL2: A Call for Simultaneous Representation Learning and Rule Learning for Graph Streams
复制标题
RL2：呼吁同时进行图流表示学习和规则学习
DOI：
10.1145/3534678.3539309
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Ge, Tingjian
中科院分区：
文献类型：
--
作者：
Liu, Qu;Ge, Tingjian
异构图流在当今的应用中非常普遍。虽然表征学习在预测准确性方面具有优势，但它在解释或推理能力方面存在固有的缺陷。早在1990年，马文·明斯基就已经意识到联结主义网络和符号规则应该共存于一个系统中，并克服彼此的缺陷。本文的目标是表明，它是可行的，同时有效地执行表示学习（连接网络）和规则学习自发的同一在线训练过程的图流。我们设计了这样一个系统，称为RL，并显示，无论是分析和经验，它是非常有效的和响应的图形流，并产生良好的结果表示学习和规则学习的预测精度和返回高质量的规则解释和构建动态贝叶斯网络。
Heterogeneous graph streams are very common in the applications today. Although representation learning has advantages in prediction accuracy, it is inherently deficient in the abilities to interpret or to reason well. It has long been realized as far back as in 1990 by Marvin Minsky that connectionist networks and symbolic rules should co-exist in a system and overcome the deficiencies of each other. The goal of this paper is to show that it is feasible to simultaneously and efficiently perform representation learning (for connectionist networks) and rule learning spontaneously out of the same online training process for graph streams. We devise such a system called RL, and show, both analytically and empirically, that it is highly efficient and responsive for graph streams, and produces good results for both representation learning and rule learning in terms of prediction accuracy and returning top-quality rules for interpretation and building dynamic Bayesian networks.
登录
查看更多内容
DOI：
10.1609/aaai.v33i01.33011544
发表时间：
2018-11
期刊：
2023 4th International Conference on Advanced Electrical and Energy Systems (AEES)
影响因子：
--
作者：
Xiang Wang;Dingxian Wang;Canran Xu;Xiangnan He;Yixin Cao;Tat-Seng Chua
通讯作者：
Xiang Wang;Dingxian Wang;Canran Xu;Xiangnan He;Yixin Cao;Tat-Seng Chua
DOI：
10.18653/v1/2020.emnlp-main.667
发表时间：
2020-04
期刊：
--
影响因子：
--
作者：
Tara Safavi;Danai Koutra;E. Meij
通讯作者：
Tara Safavi;Danai Koutra;E. Meij
回顾过去，展望未来：符号人工智能与联结人工智能
DOI：
--
发表时间：
2022
期刊：
The AI Magazine
影响因子：
--
作者：
Ai;Ashok K. Goel
通讯作者：
Ashok K. Goel
拉格朗日乘数
DOI：
10.1016/b978-0-12-240550-1.50016-0
发表时间：
2020
期刊：
Encyclopedia of Continuum Mechanics
影响因子：
--
作者：
Yan
通讯作者：
Yan