arXiv subjects

Xin Cao

Publications and source records attributed to Xin Cao.

At least 73 records · Page 4Linked to original sources

arXiv2022

Grad-Align+: Empowering Gradual Network Alignment Using Attribute Augmentation

Network alignment (NA) is the task of discovering node correspondences across different networks. Although NA methods have achieved remarkable success in a myriad of scenarios, their satisfactory performance is not without prior anchor link information and/or node attributes, which may not always be available. In this paper, we propose Grad-Align+, a novel NA method using node attribute augmentation that is quite robust to the absence of such additional information. Grad-Align+ is built upon a recent state-of-the-art NA method, the so-called Grad-Align, that gradually discovers only a part of node pairs until all node pairs are found. Specifically, Grad-Align+ is composed of the following key components: 1) augmenting node attributes based on nodes' centrality measures, 2) calculating an embedding similarity matrix extracted from a graph neural network into which the augmented node attributes are fed, and 3) gradually discovering node pairs by calculating similarities between cross-network nodes with respect to the aligned cross-network neighbor-pair. Experimental results demonstrate that Grad-Align+ exhibits (a) superiority over benchmark NA methods, (b) empirical validation of our theoretical findings, and (c) the effectiveness of our attribute augmentation module.

cs.SI↗

arXiv2022

BFE and AdaBFE: A New Approach in Learning Rate Automation for Stochastic Optimization

In this paper, a new gradient-based optimization approach by automatically adjusting the learning rate is proposed. This approach can be applied to design non-adaptive learning rate and adaptive learning rate. Firstly, I will introduce the non-adaptive learning rate optimization method: Binary Forward Exploration (BFE), and then the corresponding adaptive per-parameter learning rate method: Adaptive BFE (AdaBFE) is possible to be developed. This approach could be an alternative method to optimize the learning rate based on the stochastic gradient descent (SGD) algorithm besides the current non-adaptive learning rate methods e.g. SGD, momentum, Nesterov and the adaptive learning rate methods e.g. AdaGrad, AdaDelta, Adam... The purpose to develop this approach is not to beat the benchmark of other methods but just to provide a different perspective to optimize the gradient descent method, although some comparative study with previous methods will be made in the following sections. This approach is expected to be heuristic or inspire researchers to improve gradient-based optimization combined with previous methods.

cs.LG↗

arXiv2022

Moiré-pattern evolution couples rotational and translational friction at crystalline interfaces

The sliding motion of objects is typically governed by their friction with the underlying surface. Compared to translational friction, however, rotational friction has received much less attention. Here, we experimentally and theoretically study the rotational depinning and orientational dynamics of two-dimensional colloidal crystalline clusters on periodically corrugated surfaces in the presence of magnetically exerted torques. We demonstrate that the traversing of locally commensurate areas of the moiré pattern through the edges of clusters, which is hindered by potential barriers during cluster rotation, controls its rotational depinning. The experimentally measured depinning thresholds as a function of cluster size strikingly collapse onto a universal theoretical curve which predicts the possibility of a superlow-static-torque state for large clusters. We further reveal a cluster-size-independent rotation-translation depinning transition when lattice-matched clusters are driven jointly by a torque and a force. Our work provides guidelines to the design of nanomechanical devices that involve rotational motions on atomic surfaces.

cond-mat.soft↗

arXiv2022

Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System

Knowledge graph (KG) plays an increasingly important role in recommender systems. Recently, graph neural networks (GNNs) based model has gradually become the theme of knowledge-aware recommendation (KGR). However, there is a natural deficiency for GNN-based KGR models, that is, the sparse supervised signal problem, which may make their actual performance drop to some extent. Inspired by the recent success of contrastive learning in mining supervised signals from data itself, in this paper, we focus on exploring the contrastive learning in KG-aware recommendation and propose a novel multi-level cross-view contrastive learning mechanism, named MCCLK. Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views. Specifically, we consider the user-item graph as a collaborative view, the item-entity graph as a semantic view, and the user-item-entity graph as a structural view. MCCLK hence performs contrastive learning across three views on both local and global levels, mining comprehensive graph feature and structure information in a self-supervised manner. Besides, in semantic view, a k-Nearest-Neighbor (kNN) item-item semantic graph construction module is proposed, to capture the important item-item semantic relation which is usually ignored by previous work. Extensive experiments conducted on three benchmark datasets show the superior performance of our proposed method over the state-of-the-arts. The implementations are available at: https://github.com/CCIIPLab/MCCLK.

cs.IR↗

arXiv2022

BCOT: A Markerless High-Precision 3D Object Tracking Benchmark

Template-based 3D object tracking still lacks a high-precision benchmark of real scenes due to the difficulty of annotating the accurate 3D poses of real moving video objects without using markers. In this paper, we present a multi-view approach to estimate the accurate 3D poses of real moving objects, and then use binocular data to construct a new benchmark for monocular textureless 3D object tracking. The proposed method requires no markers, and the cameras only need to be synchronous, relatively fixed as cross-view and calibrated. Based on our object-centered model, we jointly optimize the object pose by minimizing shape re-projection constraints in all views, which greatly improves the accuracy compared with the single-view approach, and is even more accurate than the depth-based method. Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes. The annotation error is guaranteed to be less than 2mm, according to both theoretical analysis and validation experiments. We re-evaluate the state-of-the-art 3D object tracking methods with our dataset, reporting their performance ranking in real scenes. Our BCOT benchmark and code can be found at https://ar3dv.github.io/BCOT-Benchmark/.

cs.CV↗

arXiv2022

Machine Learning Solar Wind Driving Magnetospheric Convection in Tail Lobes

To quantitatively study the driving mechanisms of magnetospheric convection in the magnetotail lobes on a global scale, we utilize data from the ARTEMIS spacecraft in the deep tail and the Cluster spacecraft in the near tail. Previous work demonstrated that, in the lobes near the Moon, we can estimate the convection by utilizing ARTEMIS measurements of lunar ions velocity. In this paper, we analyze these datasets with machine learning models to determine what upstream factors drive the lobe convection in different magnetotail regions and thereby understand the mechanisms that control the dynamics of the tail lobes. Our results show that the correlations between the predicted and test convection velocities for the machine learning models (>0.75) are much better than those of the multiple linear regression model (~ 0.23 - 0.43). The systematic analysis reveals that the IMF and magnetospheric activity play an important role in influencing plasma convection in the global magnetotail lobes.

astro-ph.SR↗

arXiv2021

The Dayside Ionopause of Mars: Solar Wind Interaction, Pressure Balance, and Comparisons with Venus

Due to the lower ionospheric thermal pressure and existence of the crustal magnetism at Mars, the Martian ionopause is expected to behave differently from the ionopause at Venus. We study the solar wind interaction and pressure balance at the ionopause of Mars using both in situ and remote sounding measurements from the MARSIS (Mars Advanced Radar for Subsurface and Ionosphere Sounding) instrument on the Mars Express orbiter. We show that the magnetic pressure usually dominates the thermal pressure to hold off the solar wind at the ionopause at Mars, with only 13% of the cases where the ionospheric thermal pressure plays a more important role in pressure balance. This percentage at Venus, however, is up to 65%. We also find that the ionopause altitude at Mars decreases as the normal component of the solar wind dynamic pressure increases, similar to the altitude variation of the ionopauses at Venus. Moreover, our results show that the ionopause thickness at Mars and Venus is mainly determined by the ion gyromotion and is equivalent to about 5 ion gyroradii.

physics.space-ph↗

arXiv2021

Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain

We propose an approach for inverse reinforcement learning from hetero-domain which learns a reward function in the simulator, drawing on the demonstrations from the real world. The intuition behind the method is that the reward function should not only be oriented to imitate the experts, but should encourage actions adjusted for the dynamics difference between the simulator and the real world. To achieve this, the widely used GAN-inspired IRL method is adopted, and its discriminator, recognizing policy-generating trajectories, is modified with the quantification of dynamics difference. The training process of the discriminator can yield the transferable reward function suitable for simulator dynamics, which can be guaranteed by derivation. Effectively, our method assigns higher rewards for demonstration trajectories which do not exploit discrepancies between the two domains. With extensive experiments on continuous control tasks, our method shows its effectiveness and demonstrates its scalability to high-dimensional tasks.

cs.LG↗

arXiv2021

Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach

Due to the outstanding capability of capturing underlying data distributions, deep learning techniques have been recently utilized for a series of traditional database problems. In this paper, we investigate the possibilities of utilizing deep learning for cardinality estimation of similarity selection. Answering this problem accurately and efficiently is essential to many data management applications, especially for query optimization. Moreover, in some applications the estimated cardinality is supposed to be consistent and interpretable. Hence a monotonic estimation w.r.t. the query threshold is preferred. We propose a novel and generic method that can be applied to any data type and distance function. Our method consists of a feature extraction model and a regression model. The feature extraction model transforms original data and threshold to a Hamming space, in which a deep learning-based regression model is utilized to exploit the incremental property of cardinality w.r.t. the threshold for both accuracy and monotonicity. We develop a training strategy tailored to our model as well as techniques for fast estimation. We also discuss how to handle updates. We demonstrate the accuracy and the efficiency of our method through experiments, and show how it improves the performance of a query optimizer.

cs.DB↗

arXiv2021

Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model

Community detection, aiming to group the graph nodes into clusters with dense inner-connection, is a fundamental graph mining task. Recently, it has been studied on the heterogeneous graph, which contains multiple types of nodes and edges, posing great challenges for modeling the high-order relationship between nodes. With the surge of graph embedding mechanism, it has also been adopted to community detection. A remarkable group of works use the meta-path to capture the high-order relationship between nodes and embed them into nodes' embedding to facilitate community detection. However, defining meaningful meta-paths requires much domain knowledge, which largely limits their applications, especially on schema-rich heterogeneous graphs like knowledge graphs. To alleviate this issue, in this paper, we propose to exploit the context path to capture the high-order relationship between nodes, and build a Context Path-based Graph Neural Network (CP-GNN) model. It recursively embeds the high-order relationship between nodes into the node embedding with attention mechanisms to discriminate the importance of different relationships. By maximizing the expectation of the co-occurrence of nodes connected by context paths, the model can learn the nodes' embeddings that both well preserve the high-order relationship between nodes and are helpful for community detection. Extensive experimental results on four real-world datasets show that CP-GNN outperforms the state-of-the-art community detection methods.

cs.SI↗

arXiv2021

Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds

The existing 3D deep learning methods adopt either individual point-based features or local-neighboring voxel-based features, and demonstrate great potential for processing 3D data. However, the point based models are inefficient due to the unordered nature of point clouds and the voxel-based models suffer from large information loss. Motivated by the success of recent point-voxel representation, such as PVCNN, we propose a new convolutional neural network, called Multi Point-Voxel Convolution (MPVConv), for deep learning on point clouds. Integrating both the advantages of voxel and point-based methods, MPVConv can effectively increase the neighboring collection between point-based features and also promote independence among voxel-based features. Moreover, most of the existing approaches aim at solving one specific task, and only a few of them can handle a variety of tasks. Simply replacing the corresponding convolution module with MPVConv, we show that MPVConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MPVConv improves the accuracy of the backbone (PointNet) by up to \textbf{36\%}, and achieves higher accuracy than the voxel-based model with up to \textbf{34}$\times$ speedups. In addition, MPVConv outperforms the state-of-the-art point-based models with up to \textbf{8}$\times$ speedups. Notably, our MPVConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.

cs.CV↗

arXiv2021

Unsupervised Segmentation for Terracotta Warrior with Seed-Region-Growing CNN (SRG-Net)

The repairing work of terracotta warriors in Emperor Qinshihuang Mausoleum Site Museum is handcrafted by experts, and the increasing amounts of unearthed pieces of terracotta warriors make the archaeologists too challenging to conduct the restoration of terracotta warriors efficiently. We hope to segment the 3D point cloud data of the terracotta warriors automatically and store the fragment data in the database to assist the archaeologists in matching the actual fragments with the ones in the database, which could result in higher repairing efficiency of terracotta warriors. Moreover, the existing 3D neural network research is mainly focusing on supervised classification, clustering, unsupervised representation, and reconstruction. There are few pieces of researches concentrating on unsupervised point cloud part segmentation. In this paper, we present SRG-Net for 3D point clouds of terracotta warriors to address these problems. Firstly, we adopt a customized seed-region-growing algorithm to segment the point cloud coarsely. Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds. Finally, we combine the SRG algorithm with our improved CNN using a refinement method. This pipeline is called SRG-Net, which aims at conducting segmentation tasks on the terracotta warriors. Our proposed SRG-Net is evaluated on the terracotta warriors data and ShapeNet dataset by measuring the accuracy and the latency. The experimental results show that our SRG-Net outperforms the state-of-the-art methods. Our code is shown in Code File 1~\cite{Srgnet_2021}.

cs.CV↗

arXiv2021

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based features to process 3D model, which limits the performance of models due to the inefficient computation. Moreover, most of the existing 3D deep learning frameworks aim at solving one specific task, and only a few of them can handle a variety of tasks. Integrating both the advantages of the voxel and point-based methods, the proposed MVPConv can effectively increase the neighboring collection between point-based features and also promote the independence among voxel-based features. Simply replacing the corresponding convolution module with MVPConv, we show that MVPConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34 times speedup. In addition, MVPConv also outperforms the state-of-the-art point-based models with up to 8 times speedup. Notably, our MVPConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.

cs.CV↗

arXiv2021

Pervasive orientational and directional locking at geometrically heterogeneous sliding interfaces

Understanding the drift motion and dynamical locking of crystalline clusters on patterned substrates is important for the diffusion and manipulation of nano- and micro-scale objects on surfaces. In a previous work, we studied the orientational and directional locking of colloidal two-dimensional clusters with triangular structure driven across a triangular substrate lattice. Here we show with experiments and simulations that such locking features arise for clusters with arbitrary lattice structure sliding across arbitrary regular substrates. Similar to triangular-triangular contacts, orientational and directional locking are strongly correlated via the real- and reciprocal-space moiré patterns of the contacting surfaces. Due to the different symmetries of the surfaces in contact, however the relation between the locking orientation and the locking direction becomes more complicated compared to interfaces composed of identical lattice symmetries. We provide a generalized formalism which describes the relation between the locking orientation and locking direction with arbitrary lattice symmetries.

cond-mat.soft↗

arXiv2021

Electrostatic Waves and Electron Heating Observed over Lunar Crustal Magnetic Anomalies

Above lunar crustal magnetic anomalies, large fractions of solar wind electrons and ions can be scattered and stream back towards the solar wind flow, leading to a number of interesting effects such as electrostatic instabilities and waves. These electrostatic structures can also interact with the background plasma, resulting in electron heating and scattering. We study the electrostatic waves and electron heating observed over the lunar magnetic anomalies by analyzing data from the Acceleration, Reconnection, Turbulence, and Electrodynamics of Moon's Interaction with the Sun (ARTEMIS) spacecraft. Based on the analysis of two lunar flybys in 2011 and 2013, we find that the electron two-stream instability (ETSI) and electron cyclotron drift instability (ECDI) may play an important role in driving the electrostatic waves. We also find that ECDI, along with the modified two-stream instability (MTSI), may provide the mechanisms responsible for substantial isotropic electron heating over the lunar magnetic anomalies.

physics.space-ph↗

arXiv2020

On Efficient and Scalable Time-Continuous Spatial Crowdsourcing -- Full Version

The proliferation of advanced mobile terminals opened up a new crowdsourcing avenue, spatial crowdsourcing, to utilize the crowd potential to perform real-world tasks. In this work, we study a new type of spatial crowdsourcing, called time-continuous spatial crowdsourcing (TCSC in short). It supports broad applications for long-term continuous spatial data acquisition, ranging from environmental monitoring to traffic surveillance in citizen science and crowdsourcing projects. However, due to limited budgets and limited availability of workers in practice, the data collected is often incomplete, incurring data deficiency problem. To tackle that, in this work, we first propose an entropy-based quality metric, which captures the joint effects of incompletion in data acquisition and the imprecision in data interpolation. Based on that, we investigate quality-aware task assignment methods for both single- and multi-task scenarios. We show the NP-hardness of the single-task case, and design polynomial-time algorithms with guaranteed approximation ratios. We study novel indexing and pruning techniques for further enhancing the performance in practice. Then, we extend the solution to multi-task scenarios and devise a parallel framework for speeding up the process of optimization. We conduct extensive experiments on both real and synthetic datasets to show the effectiveness of our proposals.

cs.DB↗

arXiv2020

Inductive Link Prediction for Nodes Having Only Attribute Information

Predicting the link between two nodes is a fundamental problem for graph data analytics. In attributed graphs, both the structure and attribute information can be utilized for link prediction. Most existing studies focus on transductive link prediction where both nodes are already in the graph. However, many real-world applications require inductive prediction for new nodes having only attribute information. It is more challenging since the new nodes do not have structure information and cannot be seen during the model training. To solve this problem, we propose a model called DEAL, which consists of three components: two node embedding encoders and one alignment mechanism. The two encoders aim to output the attribute-oriented node embedding and the structure-oriented node embedding, and the alignment mechanism aligns the two types of embeddings to build the connections between the attributes and links. Our model DEAL is versatile in the sense that it works for both inductive and transductive link prediction. Extensive experiments on several benchmark datasets show that our proposed model significantly outperforms existing inductive link prediction methods, and also outperforms the state-of-the-art methods on transductive link prediction.

cs.LG↗

arXiv2018

Improved Online Wilson Score Interval Method for Community Answer Quality Ranking

In this paper, a fast and easy-to-deploy method with a strong interpretability for community answer quality ranking is proposed. This method is improved based on the Wilson score interval method [Wilson, 1927], which retains its advantages and simultaneously improve the degree of satisfaction with the ranking of the high-quality answers. The improved answer quality score considers both Wilson score interval and the spotlight index, the latter of which will be introduced in the article. This method could significantly improve the ranking of the best answers with high attention in diverse scenarios.

cs.SI↗