# Probabilistic Analogical Mapping with Semantic Relation Networks

arXiv: https://arxiv.org/abs/2103.16704 · HTML: https://mlsanity.com/paper/2103.16704/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 161 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Learning Perceptual Inference by Contrasting](https://mlsanity.com/paper/1912.00086/) (2019)
- [Learning to Make Analogies by Contrasting Abstract Relational Structure](https://mlsanity.com/paper/1902.00120/) (2019)
- [Issues in evaluating semantic spaces using word analogies](https://mlsanity.com/paper/1606.07736/) (2016)
- [Learning as the Unsupervised Alignment of Conceptual Systems](https://mlsanity.com/paper/1906.09012/) (2019)
- [Domain and Function: A Dual-Space Model of Semantic Relations and Compositions](https://mlsanity.com/paper/1309.4035/) (2013)
- [A Theory of Relation Learning and Cross-domain Generalization](https://mlsanity.com/paper/1910.05065/) (2019)
- [HUBERT Untangles BERT to Improve Transfer across NLP Tasks](https://mlsanity.com/paper/1910.12647/) (2019)
- [Distributional semantics beyond words: Supervised learning of analogy and paraphrase](https://mlsanity.com/paper/1310.5042/) (2013)

## Built on by (most cited first, 14 of 14)

- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [The Relational Bottleneck as an Inductive Bias for Efficient Abstraction](https://mlsanity.com/paper/2309.06629/) (2023)
- [LLMs as Models for Analogical Reasoning](https://mlsanity.com/paper/2406.13803/) (2024)
- [Evidence from counterfactual tasks supports emergent analogical reasoning in large language models](https://mlsanity.com/paper/2404.13070/) (2024)
- [Do large language models solve verbal analogies like children do?](https://mlsanity.com/paper/2310.20384/) (2023)
- [Zero-shot visual reasoning through probabilistic analogical mapping](https://mlsanity.com/paper/2209.15087/) (2022)
- [ARN: Analogical Reasoning on Narratives](https://mlsanity.com/paper/2310.00996/) (2023)
- [Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences](https://mlsanity.com/paper/2410.21332/) (2024)
- [Untrained neural networks can demonstrate memorization-independent abstract reasoning](https://mlsanity.com/paper/2407.17791/) (2024)
- [Few-Shot Learning of Visual Compositional Concepts through Probabilistic Schema Induction](https://mlsanity.com/paper/2505.09859/) (2025)
- [Can an Easy-to-Hard Curriculum Make Reasoning Emerge in Small Language Models? Evidence from a Four-Stage Curriculum on GPT-2](https://mlsanity.com/paper/2505.11643/) (2025)
- [Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization](https://mlsanity.com/paper/2305.18417/) (2023)
- [Silico-centric Theory of Mind](https://mlsanity.com/paper/2403.09289/) (2024)
- [A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents](https://mlsanity.com/paper/2510.22052/) (2025)

## Abstract (arXiv)

The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs. Building on a recent model of how semantic relations can be learned from non-relational word embeddings, we present a new computational model of mapping between two analogs. The model adopts a Bayesian framework for probabilistic graph matching, operating on semantic relation networks constructed from distributed representations of individual concepts and of relations between concepts. Through comparisons of model predictions with human performance in a novel mapping task requiring integration of multiple relations, as well as in several classic studies, we demonstrate that the model accounts for a broad range of phenomena involving analogical mapping by both adults and children. We also show the potential for extending the model to deal with analog retrieval. Our approach demonstrates that human-like analogical mapping can emerge from comparison mechanisms applied to rich semantic representations of individual concepts and relations.