# Probabilistic Reasoning via Deep Learning: Neural Association Models

arXiv: https://arxiv.org/abs/1603.07704 · HTML: https://mlsanity.com/paper/1603.07704/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2016.

## Built on by (most cited first, 20 of 20)

- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [Advancing Reasoning in Large Language Models: Promising Methods and Approaches](https://mlsanity.com/paper/2502.03671/) (2025)
- [SpherE: Expressive and Interpretable Knowledge Graph Embedding for Set Retrieval](https://mlsanity.com/paper/2404.19130/) (2024)
- [TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation](https://mlsanity.com/paper/2204.08401/) (2022)
- [InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities](https://mlsanity.com/paper/2202.04897/) (2022)
- [Spatio-Temporal Relation Learning for Video Anomaly Detection](https://mlsanity.com/paper/2209.13116/) (2022)
- [Self-Distillation with Meta Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2305.12209/) (2023)
- [Causal Discovery in Knowledge Graphs by Exploiting Asymmetric Properties of Non-Gaussian Distributions](https://mlsanity.com/paper/2106.01043/) (2021)
- [Discover Important Paths in the Knowledge Graph Based on Dynamic Relation Confidence](https://mlsanity.com/paper/2211.00914/) (2022)
- [Contextual Dictionary Lookup for Knowledge Graph Completion](https://mlsanity.com/paper/2306.07719/) (2023)
- [DsMtGCN: A Direction-sensitive Multi-task framework for Knowledge Graph Completion](https://mlsanity.com/paper/2306.10290/) (2023)
- [Experience and Prediction: A Metric of Hardness for a Novel Litmus Test](https://mlsanity.com/paper/2309.02534/) (2023)
- [Emulating the Human Mind: A Neural-symbolic Link Prediction Model with Fast and Slow Reasoning and Filtered Rules](https://mlsanity.com/paper/2310.13996/) (2023)
- [Survey on Embedding Models for Knowledge Graph and its Applications](https://mlsanity.com/paper/2404.09167/) (2024)
- [Neural Probabilistic Logic Learning for Knowledge Graph Reasoning](https://mlsanity.com/paper/2407.03704/) (2024)
- [A Pluggable Common Sense-Enhanced Framework for Knowledge Graph Completion](https://mlsanity.com/paper/2410.04488/) (2024)
- [A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects](https://mlsanity.com/paper/2506.11012/) (2025)
- [Logical Expressivity and Explanations for Monotonic GNNs with Scoring Functions](https://mlsanity.com/paper/2508.14091/) (2025)

## Abstract (arXiv)

In this paper, we propose a new deep learning approach, called neural association model (NAM), for probabilistic reasoning in artificial intelligence. We propose to use neural networks to model association between any two events in a domain. Neural networks take one event as input and compute a conditional probability of the other event to model how likely these two events are to be associated. The actual meaning of the conditional probabilities varies between applications and depends on how the models are trained. In this work, as two case studies, we have investigated two NAM structures, namely deep neural networks (DNN) and relation-modulated neural nets (RMNN), on several probabilistic reasoning tasks in AI, including recognizing textual entailment, triple classification in multi-relational knowledge bases and commonsense reasoning. Experimental results on several popular datasets derived from WordNet, FreeBase and ConceptNet have all demonstrated that both DNNs and RMNNs perform equally well and they can significantly outperform the conventional methods available for these reasoning tasks. Moreover, compared with DNNs, RMNNs are superior in knowledge transfer, where a pre-trained model can be quickly extended to an unseen relation after observing only a few training samples. To further prove the effectiveness of the proposed models, in this work, we have applied NAMs to solving challenging Winograd Schema (WS) problems. Experiments conducted on a set of WS problems prove that the proposed models have the potential for commonsense reasoning.