# A Novel Neural-symbolic System under Statistical Relational Learning

arXiv: https://arxiv.org/abs/2309.08931 · HTML: https://mlsanity.com/paper/2309.08931/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 38 of its 67 references that are in the map.
- First posted on arXiv 16 Sep 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 38)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [Scene Graph Generation by Iterative Message Passing](https://mlsanity.com/paper/1701.02426/) (2017)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision](https://mlsanity.com/paper/1904.12584/) (2019)
- [Visual Relationship Detection with Language Priors](https://mlsanity.com/paper/1608.00187/) (2016)
- [Graph R-CNN for Scene Graph Generation](https://mlsanity.com/paper/1808.00191/) (2018)
- [A Semantic Loss Function for Deep Learning with Symbolic Knowledge](https://mlsanity.com/paper/1711.11157/) (2017)
- [GPS-Net: Graph Property Sensing Network for Scene Graph Generation](https://mlsanity.com/paper/2003.12962/) (2020)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [Harnessing Deep Neural Networks with Logic Rules](https://mlsanity.com/paper/1603.06318/) (2016)
- [NeurASP: Embracing Neural Networks into Answer Set Programming](https://mlsanity.com/paper/2307.07700/) (2023)
- [Probabilistic Logic Neural Networks for Reasoning](https://mlsanity.com/paper/1906.08495/) (2019)
- [Hinge-Loss Markov Random Fields and Probabilistic Soft Logic](https://mlsanity.com/paper/1505.04406/) (2015)
- [Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation](https://mlsanity.com/paper/1707.09423/) (2017)
- [Pixels to Graphs by Associative Embedding](https://mlsanity.com/paper/1706.07365/) (2017)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [Efficient Probabilistic Logic Reasoning with Graph Neural Networks](https://mlsanity.com/paper/2001.11850/) (2020)
- [Embedding Symbolic Knowledge into Deep Networks](https://mlsanity.com/paper/1909.01161/) (2019)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction](https://mlsanity.com/paper/1802.05451/) (2018)
- [Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition](https://mlsanity.com/paper/1807.04979/) (2018)
- [NeuPSL: Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2205.14268/) (2022)
- [Large-Scale Visual Relationship Understanding](https://mlsanity.com/paper/1804.10660/) (2018)
- [DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning](https://mlsanity.com/paper/2207.01328/) (2022)
- [Neural Markov Logic Networks](https://mlsanity.com/paper/1905.13462/) (2019)
- [On Exploring Undetermined Relationships for Visual Relationship Detection](https://mlsanity.com/paper/1905.01595/) (2019)

## Built on by (most cited first, 1 of 1)

- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)

## Abstract (arXiv)

A key objective in the field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current methodologies in this area face limitations in integration, generalization, and interpretability. To address these challenges, we propose a neural-symbolic framework based on statistical relational learning, referred to as NSF-SRL. This framework effectively integrates deep learning models with symbolic reasoning in a mutually beneficial manner.In NSF-SRL, the results of symbolic reasoning are utilized to refine and correct the predictions made by deep learning models, while deep learning models enhance the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in supervised learning, weakly supervised and zero-shot learning tasks. Furthermore, we introduce a quantitative strategy to evaluate the interpretability of the model's predictions, visualizing the corresponding logic rules that contribute to these predictions and providing insights into the reasoning process. We believe that this approach sets a new standard for neural-symbolic systems and will drive future research in the field of general artificial intelligence.