TY - GEN
T1 - Neural Logic Reasoning
AU - Shi, Shaoyun
AU - Chen, Hanxiong
AU - Ma, Weizhi
AU - Mao, Jiaxin
AU - Zhang, Min
AU - Zhang, Yongfeng
N1 - Funding Information:
This work is supported in part by the Rutgers faculty support program, and in part by the National Key Research and Development Program of China (2018YFC0831900), Natural Science Foundation of China (61672311, 61532011), and Tsinghua University Guoqiang Research Institute. The project is also supported in part by China Postdoctoral Science Foundation and Dr. Weizhi Ma has been supported by Shuimu Tsinghua Scholar Program.
Publisher Copyright:
© 2020 ACM.
PY - 2020/10/19
Y1 - 2020/10/19
N2 - Recent years have witnessed the success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the ability of cognitive reasoning. However, the concrete ability of reasoning is critical to many theoretical and practical problems. On the other hand, traditional symbolic reasoning methods do well in making logical inference, but they are mostly hard rule-based reasoning, which limits their generalization ability to different tasks since difference tasks may require different rules. Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs. In this paper, we propose Logic-Integrated Neural Network (LINN) to integrate the power of deep learning and logic reasoning. LINN is a dynamic neural architecture that builds the computational graph according to input logical expressions. It learns basic logical operations such as AND, OR, NOT as neural modules, and conducts propositional logical reasoning through the network for inference. Experiments on theoretical task show that LINN achieves significant performance on solving logical equations and variables. Furthermore, we test our approach on the practical task of recommendation by formulating the task into a logical inference problem. Experiments show that LINN significantly outperforms state-of-the-art recommendation models in Top-K recommendation, which verifies the potential of LINN in practice.
AB - Recent years have witnessed the success of deep neural networks in many research areas. The fundamental idea behind the design of most neural networks is to learn similarity patterns from data for prediction and inference, which lacks the ability of cognitive reasoning. However, the concrete ability of reasoning is critical to many theoretical and practical problems. On the other hand, traditional symbolic reasoning methods do well in making logical inference, but they are mostly hard rule-based reasoning, which limits their generalization ability to different tasks since difference tasks may require different rules. Both reasoning and generalization ability are important for prediction tasks such as recommender systems, where reasoning provides strong connection between user history and target items for accurate prediction, and generalization helps the model to draw a robust user portrait over noisy inputs. In this paper, we propose Logic-Integrated Neural Network (LINN) to integrate the power of deep learning and logic reasoning. LINN is a dynamic neural architecture that builds the computational graph according to input logical expressions. It learns basic logical operations such as AND, OR, NOT as neural modules, and conducts propositional logical reasoning through the network for inference. Experiments on theoretical task show that LINN achieves significant performance on solving logical equations and variables. Furthermore, we test our approach on the practical task of recommendation by formulating the task into a logical inference problem. Experiments show that LINN significantly outperforms state-of-the-art recommendation models in Top-K recommendation, which verifies the potential of LINN in practice.
KW - cognitive AI
KW - collaborative reasoning
KW - machine learning
KW - machine reasoning
KW - neural networks
UR - http://www.scopus.com/inward/record.url?scp=85095551283&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85095551283&partnerID=8YFLogxK
U2 - 10.1145/3340531.3411949
DO - 10.1145/3340531.3411949
M3 - Conference contribution
AN - SCOPUS:85095551283
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 1365
EP - 1374
BT - CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 29th ACM International Conference on Information and Knowledge Management, CIKM 2020
Y2 - 19 October 2020 through 23 October 2020
ER -