The paper introduces a new way to evaluate materials graph neural networks (GNNs) by measuring how many trainable parameter‑space directions are needed to achieve good performance. Using random‑subspace intrinsic‑dimension analysis, the authors train CGCNN, ALIGNN, and DimeNet++ on six prediction tasks and plot recovery curves that separate final accuracy from the dimensional demand required to reach it. The study finds that different tasks and architectures vary in how sensitive they are to dimensional restriction, revealing insights that final error metrics alone miss.
By Shehroz Ahmad Shoaib, Kangming Li
arXiv:2607. 24818v1 Announce Type: cross Abstract: Accurate prediction of crystal properties remains a key challenge in computational materials science.
By Sanjay Chakraborty
EquiPocket is an E(3)-equivariant Graph Neural Network designed to predict ligand binding sites on proteins. It processes proteins as geometric graphs, extracting local surface atom geometry, modeling chemical and spatial relationships, and performing equivariant message passing to capture surface geometry. A dense attention output layer mitigates issues caused by variable protein sizes, and experiments show the method outperforms current state‑of‑the‑art approaches.
By Yang Zhang, Zhewei Wei, Ye Yuan, Chongxuan Li, Wenbing Huang
arXiv:2607. 08996v1 Announce Type: cross Abstract: Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties.
By Shrimon Mukherjee, Kishalay Das, Partha Basuchowdhuri, Pawan Goyal, Niloy Ganguly
arXiv:2606. 00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design.
By Shrimon Mukherjee, Kishalay Das, Partha Basuchowdhuri, Pawan Goyal, Niloy Ganguly
The paper introduces ADAPT, a lightweight machine‑learning force field that replaces graph neural networks with a direct coordinates‑in‑space Transformer encoder to model all pairwise atomic interactions. Applied to silicon point defects, ADAPT reduces force prediction error by about 22% and energy prediction error by roughly 40% compared to a state‑of‑the‑art GNN model, while also cutting computational cost. This approach addresses common GNN issues such as oversmoothing, oversquashing, and poor long‑range interaction representation, which are especially problematic for point defect modeling.
By Evan Dramko, Yihuang Xiong, Yizhi Zhu, Geoffroy Hautier, Thomas Reps, Christopher Jermaine, Anastasios Kyrillidis
arXiv:2602. 08406v2 Announce Type: replace-cross Abstract: The prediction of electromagnetic spectra for MXene-based solar absorbers, where MXenes are a family of two-dimensional transition metal carbides and nitrides, is a computationally intensive task traditionally addressed using full-wave solvers.
By Shujaat Khan, Waleed Iqbal Waseer, Muhammad Shahid Jabbar
arXiv:2607. 24785v1 Announce Type: cross Abstract: Efficient exploration of the photonic crystal (PhC) lattice design space is essential for developing photonic crystal surface-emitting lasers.
By Cen Chen, Haitao Huang, Jiazhi Mao, Feifan Xu, Zhe Zhuang, Yuxiang Ren
The paper introduces HermNet, a spectral graph neural network that uses Hermite polynomials for nodewise prediction and normalized propagation, avoiding eigendecomposition or learned bases. It compares HermNet to other complete polynomial bases, examining how coordinate choices affect optimization under limited training. Experiments on synthetic and real data show regimes where HermNet outperforms alternatives, and analyze the impact of calibration, regularization, and training duration on performance.
By Shuang Wu
arXiv:2606. 29717v1 Announce Type: cross Abstract: Predicting a material's properties from its structure is a central, fast-advancing problem in computational materials science.
By Chenmu Zhang, Boris I. Yakobson
arXiv:2607. 19042v1 Announce Type: cross Abstract: Neural hypergraphs are a natural generalization of neural networks, the reference models in modern machine learning.
By Gianluca Peri, Diego Febbe, Duccio Fanelli
arXiv:2607. 21607v1 Announce Type: cross Abstract: Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of training from solving long-range tasks.
By Ranjan Veerabhadraswamy, Ajith Jubilson Emerson