Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization

Susskind, Zachary; Arden, Bryce; John, Lizy K.; Stockton, Patrick A.; John, Eugene

doi:10.48550/arxiv.2109.06133

Cited by 8 publications

(12 citation statements)

References 19 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we discuss Neurosymbolic AI as the field of research that studies the combination of deep learning and symbolic reasoning [152,52,146]. The argument for this hybrid approach is that neural and symbolic systems can complement each other and mitigate their respective weaknesses.…”

Section: Neurosymbolic Ai: a Hybrid Approachmentioning

confidence: 99%

Neurosymbolic AI for Reasoning on Graph Structures: A Survey

DeLong¹,

Fernández²,

Whyte³

et al. 2023

Preprint

View full text Add to dashboard Cite

Neurosymbolic AI is an increasingly active area of research which aims to combine symbolic reasoning methods with deep learning to generate models with both high predictive performance and some degree of human-level comprehensibility. 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 in ways that facilitate interpretability, maintain performance, and integrate expert knowledge. Within this article, we survey a breadth of methods that perform neurosymbolic reasoning tasks on graph structures. To better compare the various methods, we propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logicallyinformed 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 applications on which these methods were primarily used and propose several prospective directions toward which this new field of research could evolve.

show abstract

Section: Neurosymbolic Ai: a Hybrid Approachmentioning

confidence: 99%

Neurosymbolic AI for Reasoning on Graph Structures: A Survey

DeLong¹,

Fernández²,

Whyte³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Neuro-symbolic AI is a valuable technology for digital twins since it can understand complex structures and reason based on certain contextual knowledge, making it beneficial for human language understanding in digital twin contexts. Neuro-symbolic AI combines the strengths of both neural networks and symbolic reasoning, which helps complex systems to incorporate domain knowledge and perform complex reasoning and decision making based on that knowledge [ 15 , 16 ]. By extracting features using deep learning techniques, neuro-symbolic AI can understand various patterns, whereas specifically defined symbolic rules drive reasoning based on knowledge [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

“…An emerging AI domain that shows potential for use in digital twin technology is neuro-symbolic AI (NSAI) [ 15 , 16 ], which blends deep learning for feature extraction with rules-based “intuition” for manipulating those features. Until the 1980s [ 37 ], rule-based or symbolic techniques dominated the field of artificial intelligence.…”

Section: Introductionmentioning

confidence: 99%

Interaction with Industrial Digital Twin Using Neuro-Symbolic Reasoning

Siyaev

Valiev

2023

Sensors

View full text Add to dashboard Cite

Digital twins have revolutionized manufacturing and maintenance, allowing us to interact with virtual yet realistic representations of the physical world in simulations to identify potential problems or opportunities for improvement. However, traditional digital twins do not have the ability to communicate with humans using natural language, which limits their potential usefulness. Although conventional natural language processing methods have proven to be effective in solving certain tasks, neuro-symbolic AI offers a new approach that leads to more robust and versatile solutions. In this paper, we propose neuro-symbolic reasoning (NSR)—a fundamental method for interacting with 3D digital twins using natural language. The method understands user requests and contexts to manipulate 3D components of digital twins and is able to read maintenance manuals and implement installations and removal procedures autonomously. A practical neuro-symbolic dataset of machine-understandable manuals, 3D models, and user queries is collected to train the neuro-symbolic reasoning interaction mechanism. The evaluation demonstrates that NSR can execute user commands accurately, achieving 96.2% accuracy on test data. The proposed method has industrial importance since it provides the technology to perform maintenance procedures, request information from manuals, and serve as a tool to interact with complex virtual machinery using natural language.

show abstract

“…The key strength of GNNs is to find meaningful representations of noisy data, that can be used for various prediction tasks [8]. Despite this advantage, as a subcategory of deep learning methods, GNNs are criticized for their limited interpretability and large data consumption [9]. Alongside, the research field of symbolic AI addresses the above-mentioned tasks.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, it helps to overcome the blackbox nature of deep learning and to improve interpretability through symbolic representations. [13] [14] [9].…”

Section: Introductionmentioning

confidence: 99%

Knowledge Enhanced Graph Neural Networks

Werner¹,

Layaïda²,

Genevès³

et al. 2023

Preprint

View full text Add to dashboard Cite

Graph data is omnipresent and has a large variety of applications such as natural science, social networks or semantic web. Though rich in information, graphs are often noisy and incomplete. Therefore, graph completion tasks such as node classification or link prediction have gained attention. On the one hand, neural methods such as graph neural networks have proven to be robust tools for learning rich representations of noisy graphs. On the other hand, symbolic methods enable exact reasoning on graphs. We propose KeGNN, a neuro-symbolic framework for learning on graph data that combines both paradigms and allows for the integration of prior knowledge into a graph neural network model. In essence, KeGNN consists of a graph neural network as a base on which knowledge enhancement layers are stacked with the objective of refining predictions with respect to prior knowledge. We instantiate KeGNN in conjunction with two standard graph neural networks: Graph Convolutional Networks and Graph Attention Networks, and evaluate KeGNN on multiple benchmark datasets for node classification.

show abstract

Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization

Cited by 8 publications

References 19 publications

Neurosymbolic AI for Reasoning on Graph Structures: A Survey

Neurosymbolic AI for Reasoning on Graph Structures: A Survey

Interaction with Industrial Digital Twin Using Neuro-Symbolic Reasoning

Knowledge Enhanced Graph Neural Networks

Contact Info

Product

Resources

About