# Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge

arXiv: https://arxiv.org/abs/2410.21341 · HTML: https://mlsanity.com/paper/2410.21341/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 28 Oct 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Retrosynthesis Prediction with Conditional Graph Logic Network](https://mlsanity.com/paper/2001.01408/) (2020)
- [Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification](https://mlsanity.com/paper/1702.05891/) (2017)
- [RetroXpert: Decompose Retrosynthesis Prediction like a Chemist](https://mlsanity.com/paper/2011.02893/) (2020)
- [Learning Graph Models for Retrosynthesis Prediction](https://mlsanity.com/paper/2006.07038/) (2020)
- [Predicting materials properties without crystal structure: Deep representation learning from stoichiometry](https://mlsanity.com/paper/1910.00617/) (2019)
- [Retrieval-based Controllable Molecule Generation](https://mlsanity.com/paper/2208.11126/) (2022)
- [Conditional Graph Information Bottleneck for Molecular Relational Learning](https://mlsanity.com/paper/2305.01520/) (2023)
- [Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks](https://mlsanity.com/paper/1901.00032/) (2018)
- [Shift-Robust Molecular Relational Learning with Causal Substructure](https://mlsanity.com/paper/2305.18451/) (2023)
- [Precursor recommendation for inorganic synthesis by machine learning materials similarity from scientific literature](https://mlsanity.com/paper/2302.02303/) (2023)
- [Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer](https://mlsanity.com/paper/2311.12856/) (2023)

## Built on by (most cited first, 9 of 9)

- [Retro-Rank-In: A Ranking-Based Approach for Inorganic Materials Synthesis Planning](https://mlsanity.com/paper/2502.04289/) (2025)
- [Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials](https://mlsanity.com/paper/2506.12557/) (2025)
- [A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools](https://mlsanity.com/paper/2506.20743/) (2025)
- [Generative Models for Crystalline Materials](https://mlsanity.com/paper/2511.22652/) (2025)
- [DiffSyn: A Generative Diffusion Approach to Materials Synthesis Planning](https://mlsanity.com/paper/2509.17094/) (2025)
- [MSP-LLM: A Unified Large Language Model Framework for Complete Material Synthesis Planning](https://mlsanity.com/paper/2602.07543/) (2026)
- [Representation of Inorganic Synthesis Reactions and Prediction: Graphical Framework and Datasets](https://mlsanity.com/paper/2512.02947/) (2025)
- [MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry](https://mlsanity.com/paper/2608.28315/) (2026)
- [CondMSP: Condition-Informed and Resource-Aware Inorganic Materials Synthesis Planning](https://mlsanity.com/paper/2610.15603/) (2026)

## Abstract (arXiv)

While inorganic retrosynthesis planning is essential in the field of chemical science, the application of machine learning in this area has been notably less explored compared to organic retrosynthesis planning. In this paper, we propose Retrieval-Retro for inorganic retrosynthesis planning, which implicitly extracts the precursor information of reference materials that are retrieved from the knowledge base regarding domain expertise in the field. Specifically, instead of directly employing the precursor information of reference materials, we propose implicitly extracting it with various attention layers, which enables the model to learn novel synthesis recipes more effectively. Moreover, during retrieval, we consider the thermodynamic relationship between target material and precursors, which is essential domain expertise in identifying the most probable precursor set among various options. Extensive experiments demonstrate the superiority of Retrieval-Retro in retrosynthesis planning, especially in discovering novel synthesis recipes, which is crucial for materials discovery. The source code for Retrieval-Retro is available at https://github.com/HeewoongNoh/Retrieval-Retro.