# Neural Class Expression Synthesis

arXiv: https://arxiv.org/abs/2111.08486 · HTML: https://mlsanity.com/paper/2111.08486/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 85 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 23 of 23)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [A Semantic Matching Energy Function for Learning with Multi-relational Data](https://mlsanity.com/paper/1301.3485/) (2013)
- [Positional Encoding to Control Output Sequence Length](https://mlsanity.com/paper/1904.07418/) (2019)
- [A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective](https://mlsanity.com/paper/2102.10062/) (2021)
- [Knowledge Graphs on the Web -- an Overview](https://mlsanity.com/paper/2003.00719/) (2020)
- [Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction](https://mlsanity.com/paper/1307.7973/) (2013)
- [Convolutional Complex Knowledge Graph Embeddings](https://mlsanity.com/paper/2008.03130/) (2020)
- [Efficient Concept Induction for Description Logics](https://mlsanity.com/paper/1812.03243/) (2018)
- [EvoLearner: Learning Description Logics with Evolutionary Algorithms](https://mlsanity.com/paper/2111.04879/) (2021)
- [Learning Description Logic Ontologies. Five Approaches. Where Do They Stand?](https://mlsanity.com/paper/2104.01193/) (2021)
- [Exact Learning of Lightweight Description Logic Ontologies](https://mlsanity.com/paper/1709.07314/) (2017)
- [Uncovering the Semantics of Wikipedia Categories](https://mlsanity.com/paper/1906.12089/) (2019)
- [Learning Concept Lengths Accelerates Concept Learning in ALC](https://mlsanity.com/paper/2107.04911/) (2021)

## Built on by (most cited first, 6 of 6)

- [LitCQD: Multi-Hop Reasoning in Incomplete Knowledge Graphs with Numeric Literals](https://mlsanity.com/paper/2304.14742/) (2023)
- [Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python](https://mlsanity.com/paper/2510.11561/) (2025)
- [SAT-Based Bounded Fitting for the Description Logic ALC](https://mlsanity.com/paper/2507.21752/) (2025)
- [Explaining ELH Concept Descriptions through Counterfactual Reasoning](https://mlsanity.com/paper/2301.05109/) (2023)
- [Improving rule mining via embedding-based link prediction](https://mlsanity.com/paper/2406.10144/) (2024)
- [Semantics-Aware Caching for Concept Learning](https://mlsanity.com/paper/2603.06506/) (2026)

## Abstract (arXiv)

Many applications require explainable node classification in knowledge graphs. Towards this end, a popular ``white-box'' approach is class expression learning: Given sets of positive and negative nodes, class expressions in description logics are learned that separate positive from negative nodes. Most existing approaches are search-based approaches generating many candidate class expressions and selecting the best one. However, they often take a long time to find suitable class expressions. In this paper, we cast class expression learning as a translation problem and propose a new family of class expression learning approaches which we dub neural class expression synthesizers. Training examples are ``translated'' into class expressions in a fashion akin to machine translation. Consequently, our synthesizers are not subject to the runtime limitations of search-based approaches. We study three instances of this novel family of approaches based on LSTMs, GRUs, and set transformers, respectively. An evaluation of our approach on four benchmark datasets suggests that it can effectively synthesize high-quality class expressions with respect to the input examples in approximately one second on average. Moreover, a comparison to state-of-the-art approaches suggests that we achieve better F-measures on large datasets. For reproducibility purposes, we provide our implementation as well as pretrained models in our public GitHub repository at https://github.com/dice-group/NeuralClassExpressionSynthesis