# Bridging the Semantic-Numerical Gap: A Numerical Reasoning Method of Cross-modal Knowledge Graph for Material Property Prediction

arXiv: https://arxiv.org/abs/2312.09744 · HTML: https://mlsanity.com/paper/2312.09744/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 76 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 15 of 15)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction](https://mlsanity.com/paper/2106.06130/) (2021)
- [N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules](https://mlsanity.com/paper/1806.09206/) (2018)
- [Molecular Contrastive Learning with Chemical Element Knowledge Graph](https://mlsanity.com/paper/2112.00544/) (2021)
- [Embedding Multimodal Relational Data for Knowledge Base Completion](https://mlsanity.com/paper/1809.01341/) (2018)
- [Incorporating Literals into Knowledge Graph Embeddings](https://mlsanity.com/paper/1802.00934/) (2018)
- [How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View](https://mlsanity.com/paper/2109.11800/) (2021)
- [LATTE: Latent Type Modeling for Biomedical Entity Linking](https://mlsanity.com/paper/1911.09787/) (2019)
- [Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation](https://mlsanity.com/paper/2011.05301/) (2020)
- [Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge](https://mlsanity.com/paper/2211.11983/) (2022)

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

- [Enhancing Large Language Models with Domain-Specific Knowledge: The Case in Topological Materials](https://mlsanity.com/paper/2409.13732/) (2024)

## Abstract (arXiv)

Using machine learning (ML) techniques to predict material properties is a crucial research topic. These properties depend on numerical data and semantic factors. Due to the limitations of small-sample datasets, existing methods typically adopt ML algorithms to regress numerical properties or transfer other pre-trained knowledge graphs (KGs) to the material. However, these methods cannot simultaneously handle semantic and numerical information. In this paper, we propose a numerical reasoning method for material KGs (NR-KG), which constructs a cross-modal KG using semantic nodes and numerical proxy nodes. It captures both types of information by projecting KG into a canonical KG and utilizes a graph neural network to predict material properties. In this process, a novel projection prediction loss is proposed to extract semantic features from numerical information. NR-KG facilitates end-to-end processing of cross-modal data, mining relationships and cross-modal information in small-sample datasets, and fully utilizes valuable experimental data to enhance material prediction. We further propose two new High-Entropy Alloys (HEA) property datasets with semantic descriptions. NR-KG outperforms state-of-the-art (SOTA) methods, achieving relative improvements of 25.9% and 16.1% on two material datasets. Besides, NR-KG surpasses SOTA methods on two public physical chemistry molecular datasets, showing improvements of 22.2% and 54.3%, highlighting its potential application and generalizability. We hope the proposed datasets, algorithms, and pre-trained models can facilitate the communities of KG and AI for materials.