UNATE: UNsupervised ATomic Embedding for crystal structures property prediction

• URL: http://arxiv.org/abs/2605.25866v1
• Date: Mon, 25 May 2026 13:55:56 GMT
• Title: UNATE: UNsupervised ATomic Embedding for crystal structures property prediction
• Abstract summary: UNATE (Unsupervised Atomic Embedding) is a framework that leverages structural information extracted from unlabeled crystal structures.<n>We show that replacing raw atomic numbers with UNATE-pretrained node embeddings yields a 2.7% improvement over the full-data baseline.<n> Notably, the benefits become more pronounced in scenarios with limited labeled data, reaching improvements of up to 10% when only 25% of the labeled data is used.
• Score: 2.217547045999963
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Accurately predicting crystal properties is critical for accelerating materials discovery, but it is often limited by scarce labeled data and costly theoretical calculations. To alleviate this, we propose UNATE (Unsupervised Atomic Embedding), a framework that leverages structural information extracted from unlabeled crystal structures. UNATE integrates an unsupervised denoising autoencoder with self-supervised contrastive learning to learn robust atomic representations, which are then used as input features for downstream property prediction. Experimental results show that replacing raw atomic numbers with UNATE-pretrained node embeddings yields a 2.7\% improvement over the full-data baseline. Notably, the benefits become more pronounced in scenarios with limited labeled data, reaching improvements of up to 10\% when only 25\% of the labeled data is used.

Related papers

• Latent Diffusion Pretraining for Crystal Property Prediction [22.088453611409182]
  We introduce a novel latent diffusion based pretraining framework, CrysLDNet, designed to mitigate data scarcity.<n>Our approach integrates a Variational Autoencoder (VAE) with a diffusion model during the pretraining stage.<n>Experiments on popular DFT datasets for property prediction reveal that CrysLDNet significantly outperforms both training-from-scratch and pretrained baselines.
  arXiv  Detail & Related papers  (2026-05-30T15:44:36Z)
• Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs [77.42033827176806]
  One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm.<n>We propose a novel Federated Model Inversion and Token Relabel framework, which trains the global model by fully exploiting all patches of synthetic images.
  arXiv  Detail & Related papers  (2026-05-11T15:49:08Z)
• Self-Conditioned Denoising for Atomistic Representation Learning [0.0]
  Self-Conditioned Denoising is a reconstruction objective that utilizes self-embeddings for conditional denoising across any domain of atomistic data.<n>We show that a small, fast GNN pretrained by SCD can achieve competitive or superior performance to larger models pretrained on significantly larger labeled or unlabeled datasets.
  arXiv  Detail & Related papers  (2026-03-17T22:52:18Z)
• Foundation-Model Surrogates Enable Data-Efficient Active Learning for Materials Discovery [12.870479903068665]
  In-Context Active Learning replaces conventional surrogates with TabPFN.<n> TabPFN is a transformer-based foundation model pre-trained on millions of synthetic regression tasks.<n>It delivers strong small-data regression performance and well-calibrated predictive uncertainty.
  arXiv  Detail & Related papers  (2026-03-13T01:57:09Z)
• From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection [89.52759572485276]
  ARC is a few-shot generalist GAD method that leverages in-context learning and requires only a few labeled normal samples at inference time.<n> ARC and ARC_zero effectively detect anomalies, exhibit strong generalization ability, and perform efficiently under few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2026-02-21T10:59:00Z)
• SemiETPicker: Fast and Label-Efficient Particle Picking for CryoET Tomography Using Semi-Supervised Learning [10.415301702950376]
  We present a fast, label-efficient semi-supervised framework that exploits unlabeled CryoET data.<n>Our framework consists of two components: (i) an end-to-end heatmap-supervised detection model inspired by keypoint detection, and (ii) a teacher-student co-training mechanism that enhances performance under sparse labeling conditions.
  arXiv  Detail & Related papers  (2025-10-25T23:09:22Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking [85.68235482145091]
  Large-scale speech datasets have become valuable intellectual property.<n>We propose a novel dataset ownership verification method.<n>Our approach introduces a clustering-based backdoor watermark (CBW)<n>We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-02T02:02:57Z)
• A Cartesian Encoding Graph Neural Network for Crystal Structures Property Prediction: Application to Thermal Ellipsoid Estimation [3.832124825311177]
  In diffraction-based crystal structure analysis, thermal ellipsoids, quantified via Anisotropic Displacement Parameters (ADPs), are critical yet challenging to determine.<n>This paper introduces CartNet, a novel graph neural network (GNN) for efficiently predicting crystal properties by encoding atomic geometry into Cartesian coordinates alongside the crystal temperature.<n>CartNet significantly reduces computational costs and outperforms existing methods in ADP prediction by 10.87%, while delivering a 34.77% improvement over theoretical approaches.
  arXiv  Detail & Related papers  (2025-01-30T14:24:03Z)
• Taming Overconfident Prediction on Unlabeled Data from Hindsight [50.9088560433925]
  Minimizing prediction uncertainty on unlabeled data is a key factor to achieve good performance in semi-supervised learning. This paper proposes a dual mechanism, named ADaptive Sharpening (ADS), which first applies a soft-threshold to adaptively mask out determinate and negligible predictions. ADS significantly improves the state-of-the-art SSL methods by making it a plug-in.
  arXiv  Detail & Related papers  (2021-12-15T15:17:02Z)
• RNA Secondary Structure Prediction By Learning Unrolled Algorithms [70.09461537906319]
  In this paper, we propose an end-to-end deep learning model, called E2Efold, for RNA secondary structure prediction. The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled algorithm for constrained programming as the template for deep architectures to enforce constraints. With comprehensive experiments on benchmark datasets, we demonstrate the superior performance of E2Efold.
  arXiv  Detail & Related papers  (2020-02-13T23:21:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.