Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915096296423424 |
|---|---|
| author | DeLong, Lauren Nicole Mir, Ramon Fernández Fleuriot, Jacques D. |
| author_facet | DeLong, Lauren Nicole Mir, Ramon Fernández Fleuriot, Jacques D. |
| contents | Neurosymbolic AI is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on knowledge graphs and propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logically-informed embedding approaches, (2) embedding approaches with logical constraints, and (3) rule learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the unique characteristics and limitations of these methods, then propose several prospective directions toward which this field of research could evolve. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_07200 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey DeLong, Lauren Nicole Mir, Ramon Fernández Fleuriot, Jacques D. Artificial Intelligence Logic in Computer Science Machine Learning Neurosymbolic AI is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on knowledge graphs and propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logically-informed embedding approaches, (2) embedding approaches with logical constraints, and (3) rule learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the unique characteristics and limitations of these methods, then propose several prospective directions toward which this field of research could evolve. |
| title | Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey |
| topic | Artificial Intelligence Logic in Computer Science Machine Learning |
| url | https://arxiv.org/abs/2302.07200 |