Enhancing composition-based materials property prediction by cross-modal knowledge transfer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908630986522624 |
|---|---|
| author | Rubtsov, Ivan Dudakov, Ivan Kuratov, Yuri Korolev, Vadim |
| author_facet | Rubtsov, Ivan Dudakov, Ivan Kuratov, Yuri Korolev, Vadim |
| contents | Crystal graph neural networks are widely applicable in modeling experimentally synthesized compounds and hypothetical materials with unknown synthesizability. In contrast, structure-agnostic predictive algorithms allow exploring previously inaccessible domains of chemical space. Here we present a universal approach for enhancing composition-based materials property prediction by means of cross-modal knowledge transfer. Two formulations are proposed: implicit transfer involves pretraining chemical language models on multimodal embeddings, whereas explicit transfer suggests generating crystal structures and implementing structure-aware predictors. The proposed approaches were benchmarked on LLM4Mat-Bench and MatBench tasks, achieving state-of-the-art performance in 25 out of 32 cases. In addition, we demonstrated how another modeling aspect of chemical language models - interpretability - benefits from applying a game-theoretic approach, which is able to incorporate high-order feature interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing composition-based materials property prediction by cross-modal knowledge transfer Rubtsov, Ivan Dudakov, Ivan Kuratov, Yuri Korolev, Vadim Materials Science Computational Physics Crystal graph neural networks are widely applicable in modeling experimentally synthesized compounds and hypothetical materials with unknown synthesizability. In contrast, structure-agnostic predictive algorithms allow exploring previously inaccessible domains of chemical space. Here we present a universal approach for enhancing composition-based materials property prediction by means of cross-modal knowledge transfer. Two formulations are proposed: implicit transfer involves pretraining chemical language models on multimodal embeddings, whereas explicit transfer suggests generating crystal structures and implementing structure-aware predictors. The proposed approaches were benchmarked on LLM4Mat-Bench and MatBench tasks, achieving state-of-the-art performance in 25 out of 32 cases. In addition, we demonstrated how another modeling aspect of chemical language models - interpretability - benefits from applying a game-theoretic approach, which is able to incorporate high-order feature interactions. |
| title | Enhancing composition-based materials property prediction by cross-modal knowledge transfer |
| topic | Materials Science Computational Physics |
| url | https://arxiv.org/abs/2511.03371 |