Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems. To address this challenge, we introduce **Neural P$^3$M**, a versatile enhancer of geometric GNNs to expand the scope of their capabilities by incorporating mesh points alongside atoms and reimaging traditional mathematical operations in a trainable manner. Neural P$^3$M exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces, outperforming on benchmarks such as the MD22 dataset. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures. Codes are available at https://github.com/OnlyLoveKFC/Neural_P3M.

The widespread adoption of Transformer architectures in various data modalities has opened new avenues for the applications in molecular modeling. Nevertheless, it remains elusive that whether the Transformer-based architecture can do molecular modeling as good as equivariant GNNs. In this paper, by designing Interatomic Positional Encoding (IPE) that parameterizes atomic environments as Transformer's positional encodings, we propose Geoformer, a novel geometric Transformer to effectively model molecular structures for various molecular property prediction. We evaluate Geoformer on several benchmarks, including the QM9 dataset and the recently proposed Molecule3D dataset. Compared with both Transformers and equivariant GNN models, Geoformer outperforms the state-of-the-art (SoTA) algorithms on QM9, and achieves the best performance on Molecule3D for both random and scaffold splits. By introducing IPE, Geoformer paves the way for molecular geometric modeling based on Transformer architecture. Codes are available at https://github.com/microsoft/AI2BMD/tree/Geoformer.

Detecting hot social events (e.g., political scandal, momentous meetings, natural hazards, etc.) from social messages is crucial as it highlights significant happenings to help people understand the real world. On account of the streaming nature of social messages, incremental social event detection models in acquiring, preserving, and updating messages over time have attracted great attention. However, the challenge is that the existing event detection methods towards streaming social messages are generally confronted with ambiguous events features, dispersive text contents, and multiple languages, and hence result in low accuracy and generalization ability. In this paper, we present a novel reinForced, incremental and cross-lingual social Event detection architecture, namely FinEvent, from streaming social messages. Concretely, we first model social messages into heterogeneous graphs integrating both rich meta-semantics and diverse meta-relations, and convert them to weighted multi-relational message graphs. Second, we propose a new reinforced weighted multi-relational graph neural network framework by using a Multi-agent Reinforcement Learning algorithm to select optimal aggregation thresholds across different relations/edges to learn social message embeddings. To solve the long-tail problem in social event detection, a balanced sampling strategy guided Contrastive Learning mechanism is designed for incremental social message representation learning. Third, a new Deep Reinforcement Learning guided density-based spatial clustering model is designed to select the optimal minimum number of samples required to form a cluster and optimal minimum distance between two clusters in social event detection tasks. Finally, we implement incremental social message representation learning based on knowledge preservation on the graph neural network and achieve the transferring cross-lingual social event detection. We conduct extensive experiments to evaluate the FinEvent on Twitter streams, demonstrating a significant and consistent improvement in model quality with 14%-118%, 8%-170%, and 2%-21% increases in performance on offline, online, and cross-lingual social event detection tasks.

Cloud workload turning point is either a local peak point standing for workload pressure or a local valley point standing for resource waste. Predicting such critical points is important to give warnings to system managers to take precautionary measures aimed at achieving high resource utilization, quality of service (QoS), and profit of the investment. Existing researches mainly focus more on the workload's future point value prediction only, whereas trend-based turning point prediction is not considered. Moreover, one of the most critical challenges during the prediction is the fact that traditional trend prediction methods which succeed in financial and industrial areas, etc., have a weak ability to represent the cloud features, which means that they cannot describe the highly-variable cloud workloads time series. This article introduces a novel cloud workload turning point prediction approach based on cloud feature-enhanced deep learning. First, we establish a turning point prediction model of cloud server workload considering cloud workload features. Then, a cloud feature-enhanced deep learning model is designed for workload turning point prediction. Experiments on the most famous Google cluster demonstrate the effectiveness of our model compared with state-of-the-art models. To the best of our knowledge, this article is the first systematic research on turning point-based trend prediction of cloud workload time series by cloud feature-enhanced deep learning.

The ice, cloud, and land elevation satellite-2 (ICESat-2) is equipped with a photon-counting laser altimeter system and demonstrates outstanding ability to measure elevations in the ever-changing earth. However, the ICESat-2 data contain several noise photons affected by solar returns, and there are no reference data of signal or noise photons for evaluating the performance of denoising algorithms. In this letter, we propose a self-adaptive denoising algorithm based on a genetic algorithm (SADA-GA) for the ICESat-2 data, which uses the real-coded genetic algorithm to adaptively search for the global optimal denoising parameters in different data sets. The SADA-GA addresses the limitation of the selection method of the two parameters K and T in the localized statistics-based algorithm that normally cannot be applied to different data sets. To evaluate the algorithm performance, we created an ICESat-2 data set named WHU-PCL and compared the SADA-GA with two classic methods. The qualitative and quantitative analyses showed that our method can extract signal photons more efficiently from different ICESat-2 data sets and achieve the$F$value of 0.99 in nighttime data. In addition, we analyzed the factors that affect the SADA-GA performance and found that the signal-to-noise ratio (SNR) is the most important parameter.

High-resolution synthetic aperture radar (SAR) satellites have become an important way to observe the earth. However, the geometric positioning accuracy of SAR satellite images across different times and spaces is an important factor affecting the realization of global remote sensing applications. In this study, a multimode hybrid geometric calibration method that incorporates an atmospheric propagation delay correction and that can be used to detect systematic errors affecting the geometric positioning accuracy of SAR satellites is described. The spatiotemporal variation reasons of geometric positioning error sources for spaceborne SAR are then analyzed. Finally, the stability of geometric positioning accuracy is evaluated using the described method on data extracted from Yaogan-13 (YG-13) SAR satellite images with long time series and multiple test areas in China. The results reveal that during the study period (2015–2017), the geometric positioning accuracy of the YG-13 SAR system was relatively stable and is better than 3 m regardless of the spatial distribution, after removal of systematic pulse-dependent slant range errors and atmospheric correction. Furthermore, the validation results provide a reference for the design of SAR satellite systems, the establishment of calibration periods, and quantitative remote sensing application.

Anomalous users detection in social network is an imperative task for security problems. Motivated by the great power of Graph Neural Networks(GNNs), many current researches adopt GNN-based detectors to reveal the anomalous users. However, the increasing scale of social activities, explosive growth of users and manifold technical disguise render the user detection a difficult task. In this paper, we propose an innovate Relevance-aware Anomalous Users Detection model (RAU-GNN) to obtain a fine-grained detection result. RAU-GNN first extracts multiple relations of all types of users in social network, including both benign and anomalous users, and accordingly constructs the multiple user relation graph. Secondly, we employ relevance-aware GNN framework to learn the hidden features of users, and discriminate the anomalous users after discriminating. Concretely, by integrating Graph Convolution Network(GCN) and Graph Attention Network(GAT), we design a GCN-based relation fusion layer to aggregate initial information from different relations, and a GAT-based embedding layer to obtain the high-level embeddings. Lastly, we feed the learned representations to the following GNN layer in order to consolidate the node embedding by aggregating the final users' embeddings. We conduct extensive experiment on real-world datasets. The experimental results show that our approach can achieve high accuracy for anomalous users detection.

The background noise of the photon counting laser point cloud data is large, and the distribution of point cloud density is uneven. In this paper, a point cloud denoising algorithm based on local distance weighted statistics is proposed to solve the problem that the noise point and non-noise are difficult to distinguish when the density of point cloud is low. By adding the weight function, the density difference between noise points and non-noise points is increased when the density of point cloud is low. This method can effectively remove the noise points and thus extract a continuous and complete effective point cloud. Besides, this paper compered the proposed method with the traditional point cloud denoising algorithm based on local distance statistics to verify the efficiency of the proposed algorithm. The results show that the algorithm in this paper has more advantages in dealing with the uneven density of laser point cloud.