From Statistical Relational to Neuro-Symbolic Artificial Intelligence

Raedt, Luc De; Dumančić, Sebastijan; Manhaeve, Robin; Marra, Giuseppe

doi:10.24963/ijcai.2020/688

Cited by 84 publications

(55 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To exploit the complex background knowledge expressed by formal languages directly, Statistical Relational (StarAI) and Neural Symbolic (NeSy) AI [De Raedt et al, 2020;Garcez et al, 2019] try to use probabilistic inference or other differentiable functions to approximate logical inference Dong et al, 2019;Manhaeve et al, 2018;Donadello et al, 2017]. However, they require a pre-defined symbolic knowledge base and only train the attached neural/probabilistic models due to the highly complex interface between the neural and symbolic modules.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, many researchers propose to break the end-toend learning pipeline apart, and build a hybrid model that consists of smaller modules where each of them only accounts for one specific function [Glasmachers, 2017]. A representative branch in this line of research is Neuro-Symbolic (NeSy) AI [De Raedt et al, 2020;Garcez et al, 2019] aiming to bridge System 1 and System 2 AI [Kahneman, 2011;Bengio, 2017], i.e., neural-network-based machine learning and symbolic-based relational inference.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Abductive Knowledge Induction from Raw Data

Dai

Muggleton

2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

For many reasoning-heavy tasks with raw inputs, it is challenging to design an appropriate end-to-end pipeline to formulate the problem-solving process. Some modern AI systems, e.g., Neuro-Symbolic Learning, divide the pipeline into sub-symbolic perception and symbolic reasoning, trying to utilise data-driven machine learning and knowledge-driven problem-solving simultaneously. However, these systems suffer from the exponential computational complexity caused by the interface between the two components, where the sub-symbolic learning model lacks direct supervision, and the symbolic model lacks accurate input facts. Hence, they usually focus on learning the sub-symbolic model with a complete symbolic knowledge base while avoiding a crucial problem: where does the knowledge come from? In this paper, we present Abductive Meta-Interpretive Learning (MetaAbd) that unites abduction and induction to learn neural networks and logic theories jointly from raw data. Experimental results demonstrate that MetaAbd not only outperforms the compared systems in predictive accuracy and data efficiency but also induces logic programs that can be re-used as background knowledge in subsequent learning tasks. To the best of our knowledge, MetaAbd is the first system that can jointly learn neural networks from scratch and induce recursive first-order logic theories with predicate invention.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Abductive Knowledge Induction from Raw Data

Dai

Muggleton

2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…In [49] the authors survey hybrid ("neural-symbolic") systems along eight different dimensions. We briefly describe each of these, and discuss their relationship to the distinction made in our own work.…”

Section: Kautz Typesmentioning

confidence: 99%

Modular design patterns for hybrid learning and reasoning systems

et al. 2021

View full text Add to dashboard Cite

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognized as one of the key challenges of modern AI. Recent years have seen a large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse, mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper, we analyze a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems organized in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognized until now. Finally, our design patterns extend and refine Kautz’s earlier attempt at categorizing neuro-symbolic architectures.

show abstract

“…The higher the weight, the higher is the probability of rule being true. SRL approaches can be broadly classified into proof-theoretic or model-theoretic approaches based on the inference technique used (De Raedt et al, 2020). In proof-theoretic approaches, a sequence of logical reasoning steps or a proof is generated and this is used to define a probability distribution.…”

Section: Statistical Relational Learningmentioning

confidence: 99%

A comparison of statistical relational learning and graph neural networks for aggregate graph queries

2021

View full text Add to dashboard Cite

Statistical relational learning (SRL) and graph neural networks (GNNs) are two powerful approaches for learning and inference over graphs. Typically, they are evaluated in terms of simple metrics such as accuracy over individual node labels. Complex aggregate graph queries (AGQ) involving multiple nodes, edges, and labels are common in the graph mining community and are used to estimate important network properties such as social cohesion and influence. While graph mining algorithms support AGQs, they typically do not take into account uncertainty, or when they do, make simplifying assumptions and do not build full probabilistic models. In this paper, we examine the performance of SRL and GNNs on AGQs over graphs with partially observed node labels. We show that, not surprisingly, inferring the unobserved node labels as a first step and then evaluating the queries on the fully observed graph can lead to sub-optimal estimates, and that a better approach is to compute these queries as an expectation under the joint distribution. We propose a sampling framework to tractably compute the expected values of AGQs. Motivated by the analysis of subgroup cohesion in social networks, we propose a suite of AGQs that estimate the community structure in graphs. In our empirical evaluation, we show that by estimating these queries as an expectation, SRL-based approaches yield up to a 50-fold reduction in average error when compared to existing GNN-based approaches.

show abstract

From Statistical Relational to Neuro-Symbolic Artificial Intelligence

Cited by 84 publications

References 7 publications

Abductive Knowledge Induction from Raw Data

Abductive Knowledge Induction from Raw Data

Modular design patterns for hybrid learning and reasoning systems

A comparison of statistical relational learning and graph neural networks for aggregate graph queries

Contact Info

Product

Resources

About