{"slug": "bdip-net-dual-interaction-graph-learning-for-property-prediction-of-bilayer", "title": "BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials", "summary": "Researchers propose BDIP-Net, a graph neural network that explicitly models intra-layer and inter-layer interactions for property prediction of bilayer materials, outperforming existing approaches on the BiDB, HetDB, and SAMBA datasets. The framework also uses a MatterSim-D3-based workflow to generate DFT-quality bilayer structures at reduced computational cost.", "body_md": "arXiv:2608.14640v1 Announce Type: new\nAbstract: Stacked bilayer materials exhibit rich stacking-dependent properties driven by the interplay between strong intra-layer bonding and weak inter-layer van der Waals interactions. The computational discovery of such materials is challenging because accurate structure generation typically relies on expensive DFT-based optimization, while existing machine-learning models often fail to explicitly distinguish different interaction types during property prediction. To address these challenges, we propose a machine-learning framework for efficient construction and property prediction of stacked bilayer materials. The framework employs a MatterSim-D3-based structural optimization workflow to generate DFT-quality bilayer structures from monolayer building blocks and stacking configurations at substantially reduced computational cost. For property prediction, we introduce BDIP-Net (Bilayer Dual-Interaction Potential Network), a graph neural network that explicitly models intra-layer and inter-layer interactions through interaction-specific potential representations and adaptive message fusion. We evaluate the proposed framework on BiDB, HetDB, and SAMBA, encompassing homobilayers, heterobilayers, and twisted bilayer systems. Results show that the MatterSim-D3-based workflow closely reproduces DFT-PBE-D3 optimized structures, while BDIP-Net consistently outperforms existing graph neural network and potential-based approaches for bilayer property prediction.", "url": "https://wpnews.pro/news/bdip-net-dual-interaction-graph-learning-for-property-prediction-of-bilayer", "canonical_source": "https://arxiv.org/abs/2608.14640", "published_at": "2026-08-18 04:00:00+00:00", "updated_at": "2026-08-18 04:12:55.663283+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "artificial-intelligence"], "entities": ["BDIP-Net", "MatterSim-D3", "BiDB", "HetDB", "SAMBA"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/bdip-net-dual-interaction-graph-learning-for-property-prediction-of-bilayer", "markdown": "https://wpnews.pro/news/bdip-net-dual-interaction-graph-learning-for-property-prediction-of-bilayer.md", "text": "https://wpnews.pro/news/bdip-net-dual-interaction-graph-learning-for-property-prediction-of-bilayer.txt", "jsonld": "https://wpnews.pro/news/bdip-net-dual-interaction-graph-learning-for-property-prediction-of-bilayer.jsonld"}}