In the field of material science, the analysis of the properties of crystalline materials is of key importance. Recently, machine learning has become a prominent tool for predicting the properties of materials based on their structure. However, the application of machine learning to crystal property prediction faces two significant challenges. The first is the scarcity of labeled data, due to the time-consuming and resource-intensive process of crystal property labeling. The second is the importance of leveraging specialized knowledge when performing crystal structure analysis, which requires adapting machine learning methods specifically for the crystal domain. In this paper, we propose a new semi-supervised framework, aKnowledge-BasedSemi-Supervised crystal property prediction (KBSS) framework, which employs consistency regularization to leverage both labeled and unlabeled data while incorporating crystal knowledge guidance. Specifically, to use unlabeled data efficiently, the KBSS framework incorporates two key modules: a knowledge-guided augmentation (KGA) module and an adaptive pseudo-label filtering (APF) module. The KGA module utilizes the Monte Carlo method to leverage knowledge from the crystal domain to guide weak and strong augmentations of crystal structures. The APF module enhances the pseudo-labeling process for unlabeled crystal data by enabling task-guided uncertainty adjustment and category-aware pseudo-label selection. The experimental results show that KBSS achieves state-of-the-art performance. All code is publicly available athttps://github.com/HaominYu0/KBSS.

Predicting channel state information (CSI) is a fundamental element in wireless communications systems. An accurate CSI estimation and prediction is critical to the system performance. This paper introduces a recurrent neural network (RNN) based approach for real-time prediction in real-world non-stationary channels. It uses the recent history data for online training, followed by prediction employing the trained model, in order to adapt to the changing channel and obtain a more accurate CSI prediction compared to conventional methods. Furthermore, the proposed method needs no additional knowledge, such as the internal properties of the channel itself, or the external features that affect the channel propagation, greatly facilitating its use in practical systems. Simulation results show that the proposed adaptive and parameter free recurrent neural structure (APF-RNS) outperforms the existing methods under a dynamically changing non-stationary environment. Therefore, the proposed online training based RNN approach is a promising method for channel prediction in wireless communications.