Searcharxiv⌕ Search

arXiv subjects

Xin Cao

Publications and source records attributed to Xin Cao.

At least 55 records · Page 3Linked to original sources
arXiv2023

An Augmented Index-based Efficient Community Search for Large Directed Graphs

Given a graph G and a query vertex q, the topic of community search (CS), aiming to retrieve a dense subgraph of G containing q, has gained much attention. Most existing works focus on undirected graphs which overlooks the rich information carried by the edge directions. Recently, the problem of community search over directed graphs (or CSD problem) has been studied; it finds a connected subgraph containing q, where the in-degree and out-degree of each vertex within the subgraph are at least k and l, respectively. However, existing solutions are inefficient, especially on large graphs. To tackle this issue, in this paper, we propose a novel index called D-Forest, which allows a CSD query to be completed within the optimal time cost. We further propose efficient index construction methods. Extensive experiments on six real large graphs show that our index-based query algorithm is up to two orders of magnitude faster than existing solutions.

cs.DB↗
arXiv2023

LMSFC: A Novel Multidimensional Index based on Learned Monotonic Space Filling Curves

The recently proposed learned indexes have attracted much attention as they can adapt to the actual data and query distributions to attain better search efficiency. Based on this technique, several existing works build up indexes for multi-dimensional data and achieve improved query performance. A common paradigm of these works is to (i) map multi-dimensional data points to a one-dimensional space using a fixed space-filling curve (SFC) or its variant and (ii) then apply the learned indexing techniques. We notice that the first step typically uses a fixed SFC method, such as row-major order and z-order. It definitely limits the potential of learned multi-dimensional indexes to adapt variable data distributions via different query workloads. In this paper, we propose a novel idea of learning a space-filling curve that is carefully designed and actively optimized for efficient query processing. We also identify innovative offline and online optimization opportunities common to SFC-based learned indexes and offer optimal and/or heuristic solutions. Experimental results demonstrate that our proposed method, LMSFC, outperforms state-of-the-art non-learned or learned methods across three commonly used real-world datasets and diverse experimental settings.

cs.DB↗
arXiv2023

On the Power of Gradual Network Alignment Using Dual-Perception Similarities

Network alignment (NA) is the task of finding the correspondence of nodes between two networks based on the network structure and node attributes. Our study is motivated by the fact that, since most of existing NA methods have attempted to discover all node pairs at once, they do not harness information enriched through interim discovery of node correspondences to more accurately find the next correspondences during the node matching. To tackle this challenge, we propose Grad-Align, a new NA method that gradually discovers node pairs by making full use of node pairs exhibiting strong consistency, which are easy to be discovered in the early stage of gradual matching. Specifically, Grad-Align first generates node embeddings of the two networks based on graph neural networks along with our layer-wise reconstruction loss, a loss built upon capturing the first-order and higher-order neighborhood structures. Then, nodes are gradually aligned by computing dual-perception similarity measures including the multi-layer embedding similarity as well as the Tversky similarity, an asymmetric set similarity using the Tversky index applicable to networks with different scales. Additionally, we incorporate an edge augmentation module into Grad-Align to reinforce the structural consistency. Through comprehensive experiments using real-world and synthetic datasets, we empirically demonstrate that Grad-Align consistently outperforms state-of-the-art NA methods.

cs.SI↗
arXiv2023

SR-R$^2$KAC: Improving Single Image Defocus Deblurring

We propose an efficient deep learning method for single image defocus deblurring (SIDD) by further exploring inverse kernel properties. Although the current inverse kernel method, i.e., kernel-sharing parallel atrous convolution (KPAC), can address spatially varying defocus blurs, it has difficulty in handling large blurs of this kind. To tackle this issue, we propose a Residual and Recursive Kernel-sharing Atrous Convolution (R$^2$KAC). R$^2$KAC builds on a significant observation of inverse kernels, that is, successive use of inverse-kernel-based deconvolutions with fixed size helps remove unexpected large blurs but produces ringing artifacts. Specifically, on top of kernel-sharing atrous convolutions used to simulate multi-scale inverse kernels, R$^2$KAC applies atrous convolutions recursively to simulate a large inverse kernel. Specifically, on top of kernel-sharing atrous convolutions, R$^2$KAC stacks atrous convolutions recursively to simulate a large inverse kernel. To further alleviate the contingent effect of recursive stacking, i.e., ringing artifacts, we add identity shortcuts between atrous convolutions to simulate residual deconvolutions. Lastly, a scale recurrent module is embedded in the R$^2$KAC network, leading to SR-R$^2$KAC, so that multi-scale information from coarse to fine is exploited to progressively remove the spatially varying defocus blurs. Extensive experimental results show that our method achieves the state-of-the-art performance.

cs.CV↗
arXiv2023

Criteria Tell You More than Ratings: Criteria Preference-Aware Light Graph Convolution for Effective Multi-Criteria Recommendation

The multi-criteria (MC) recommender system, which leverages MC rating information in a wide range of e-commerce areas, is ubiquitous nowadays. Surprisingly, although graph neural networks (GNNs) have been widely applied to develop various recommender systems due to GNN's high expressive capability in learning graph representations, it has been still unexplored how to design MC recommender systems with GNNs. In light of this, we make the first attempt towards designing a GNN-aided MC recommender system. Specifically, rather than straightforwardly adopting existing GNN-based recommendation methods, we devise a novel criteria preference-aware light graph convolution CPA-LGC method, which is capable of precisely capturing the criteria preference of users as well as the collaborative signal in complex high-order connectivities. To this end, we first construct an MC expansion graph that transforms user--item MC ratings into an expanded bipartite graph to potentially learn from the collaborative signal in MC ratings. Next, to strengthen the capability of criteria preference awareness, CPA-LGC incorporates newly characterized embeddings, including user-specific criteria-preference embeddings and item-specific criterion embeddings, into our graph convolution model. Through comprehensive evaluations using four real-world datasets, we demonstrate (a) the superiority over benchmark MC recommendation methods and benchmark recommendation methods using GNNs with tremendous gains, (b) the effectiveness of core components in CPA-LGC, and (c) the computational efficiency.

cs.SI↗
arXiv2023

Weighted Sampling for Masked Language Modeling

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare tokens is poor and PLMs have limited performance on downstream tasks. To alleviate this frequency bias issue, we propose two simple and effective Weighted Sampling strategies for masking tokens based on the token frequency and training loss. We apply these two strategies to BERT and obtain Weighted-Sampled BERT (WSBERT). Experiments on the Semantic Textual Similarity benchmark (STS) show that WSBERT significantly improves sentence embeddings over BERT. Combining WSBERT with calibration methods and prompt learning further improves sentence embeddings. We also investigate fine-tuning WSBERT on the GLUE benchmark and show that Weighted Sampling also improves the transfer learning capability of the backbone PLM. We further analyze and provide insights into how WSBERT improves token embeddings.

cs.CL↗
arXiv2023

Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling

Definition modeling is an important task in advanced natural language applications such as understanding and conversation. Since its introduction, it focus on generating one definition for a target word or phrase in a given context, which we refer to as Single Definition Modeling (SDM). However, this approach does not adequately model the correlations and patterns among different contexts and definitions of words. In addition, the creation of a training dataset for SDM requires significant human expertise and effort. In this paper, we carefully design a new task called Multiple Definition Modeling (MDM) that pool together all contexts and definition of target words. We demonstrate the ease of creating a model as well as multiple training sets automatically. % In the experiments, we demonstrate and analyze the benefits of MDM, including improving SDM's performance by using MDM as the pretraining task and its comparable performance in the zero-shot setting.

cs.CL↗
arXiv2023

Surface quantum dots with pure, coherent, and blinking-free single photon emission

The surface of semiconductor nanostructures has a major impact on their electronic and optical properties. Disorder and defects in the surface layer typically cause degradation of charge carrier transport and radiative recombination dynamics. However, surface vicinity is inevitable for many scalable nano-optical applications. Epitaxially grown quantum dots are the best candidate for high-performance single photon emission and show great potential for quantum technologies. Yet, these emitters only reveal their excellent properties if they are deeply embedded in a semiconductor host. Until today, quantum dots close to surfaces yield weak, broad, and unstable emissions. Here, we show the complete restoration of optical properties from quantum dots grown directly on a semiconductor surface. The vanishing luminescence from the as-grown sample turns into bright, ultra-stable, coherent and blinking-free single photon emission after sulphur passivation. Under quasi-resonant excitation, single photons are generated with 98.8% purity, 77% indistinguishability, linewidths down to 4 $μ$eV and 99.69% persistency across 11 orders of magnitude in time. The emission is stable even after two years and when being subjected to nanomanufacturing processes. Some long-standing stumbling blocks for surface-dominated quantum dots are thereby removed, unveiling new possibilities for hybrid nano-devices and applications in quantum communication or sensing.

cond-mat.mes-hall↗
arXiv2023

GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs

Heterogeneous graphs, which contain nodes and edges of multiple types, are prevalent in various domains, including bibliographic networks, social media, and knowledge graphs. As a fundamental task in analyzing heterogeneous graphs, relevance measure aims to calculate the relevance between two objects of different types, which has been used in many applications such as web search, recommendation, and community detection. Most of existing relevance measures focus on homogeneous networks where objects are of the same type, and a few measures are developed for heterogeneous graphs, but they often need the pre-defined meta-path. Defining meaningful meta-paths requires much domain knowledge, which largely limits their applications, especially on schema-rich heterogeneous graphs like knowledge graphs. Recently, the Graph Neural Network (GNN) has been widely applied in many graph mining tasks, but it has not been applied for measuring relevance yet. To address the aforementioned problems, we propose a novel GNN-based relevance measure, namely GSim. Specifically, we first theoretically analyze and show that GNN is effective for measuring the relevance of nodes in the graph. We then propose a context path-based graph neural network (CP-GNN) to automatically leverage the semantics in heterogeneous graphs. Moreover, we exploit CP-GNN to support relevance measures between two objects of any type. Extensive experiments demonstrate that GSim outperforms existing measures.

cs.IR↗
arXiv2023

A solid-state source of single and entangled photons at diamond SiV$^-$-center transitions operating at 80K

Large-scale quantum networks require the implementation of long-lived quantum memories as stationary nodes interacting with qubits of light. Epitaxially grown quantum dots hold great potential for the on-demand generation of single and entangled photons with high purity and indistinguishability. Coupling these emitters to memories with long coherence times enables the development of hybrid nanophotonic devices incorporating the advantages of both systems. Here we report the first GaAs/AlGaAs quantum dots grown by droplet etching and nanohole infilling method, emitting single photons with a narrow wavelength distribution (736.2 $\pm$ 1.7 nm) close to the zero-phonon line of Silicon-vacancy centers. Polarization entangled photons are generated via the biexciton-exciton cascade with a fidelity of (0.73 $\pm$ 0.09). High single photon purity is maintained from 4 K (g$^($$^2$$^)$(0) = 0.07 $\pm$ 0.02) up to 80 K (g$^($$^2$$^)$(0) = 0.11 $\pm$ 0.01), therefore making this hybrid system technologically attractive for real-world quantum photonic applications.

quant-ph↗
arXiv2023

WISK: A Workload-aware Learned Index for Spatial Keyword Queries

Spatial objects often come with textual information, such as Points of Interest (POIs) with their descriptions, which are referred to as geo-textual data. To retrieve such data, spatial keyword queries that take into account both spatial proximity and textual relevance have been extensively studied. Existing indexes designed for spatial keyword queries are mostly built based on the geo-textual data without considering the distribution of queries already received. However, previous studies have shown that utilizing the known query distribution can improve the index structure for future query processing. In this paper, we propose WISK, a learned index for spatial keyword queries, which self-adapts for optimizing querying costs given a query workload. One key challenge is how to utilize both structured spatial attributes and unstructured textual information during learning the index. We first divide the data objects into partitions, aiming to minimize the processing costs of the given query workload. We prove the NP-hardness of the partitioning problem and propose a machine learning model to find the optimal partitions. Then, to achieve more pruning power, we build a hierarchical structure based on the generated partitions in a bottom-up manner with a reinforcement learning-based approach. We conduct extensive experiments on real-world datasets and query workloads with various distributions, and the results show that WISK outperforms all competitors, achieving up to 8x speedup in querying time with comparable storage overhead.

cs.DB↗
arXiv2023

Strain control of exciton and trion spin-valley dynamics in monolayer transition metal dichalcogenides

The electron-hole exchange interaction is a fundamental mechanism that drives valley depolarization via intervalley exciton hopping in semiconductor multi-valley systems. Here, we report polarization-resolved photoluminescence spectroscopy of neutral excitons and negatively charged trions in monolayer MoSe$_2$ and WSe$_2$ under biaxial strain. We observe a marked enhancement(reduction) on the WSe$_2$ triplet trion valley polarization with compressive(tensile) strain while the trion in MoSe$_2$ is unaffected. The origin of this effect is shown to be a strain dependent tuning of the electron-hole exchange interaction. A combined analysis of the strain dependent polarization degree using ab initio calculations and rate equations shows that strain affects intervalley scattering beyond what is expected from strain dependent bandgap modulations. The results evidence how strain can be used to tune valley physics in energetically degenerate multi-valley systems.

cond-mat.mes-hall↗
arXiv2023

Memory induced Magnus effect

Spinning objects which move through air or liquids experience a Magnus force. This effect is commonly exploited in ball sports but also of considerable importance for applications and fundamental science. Opposed to large objects where Magnus forces are strong, they are only weak at small scales and eventually vanish for overdamped micron-sized particles in simple liquids. Here we demonstrate an about one-million-fold enhanced Magnus force of spinning colloids in viscoelastic fluids. Such fluids are characterized by a time-delayed response to external perturbations which causes a deformation of the fluidic network around the moving particle. When the particle additionally spins, the deformation field becomes misaligned relative to the particle's moving direction, leading to a force perpendicular to the direction of travel and the spinning axis. The presence of strongly enhanced memory-induced Magnus forces at microscales opens novel applications for particle sorting and steering, the creation and visualization of anomalous flows and more.

cond-mat.soft↗
arXiv2023

MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

Keyphrase extraction (KPE) automatically extracts phrases in a document that provide a concise summary of the core content, which benefits downstream information retrieval and NLP tasks. Previous state-of-the-art (SOTA) methods select candidate keyphrases based on the similarity between learned representations of the candidates and the document. They suffer performance degradation on long documents due to discrepancy between sequence lengths which causes mismatch between representations of keyphrase candidates and the document. In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document. We further develop a KPE-oriented BERT (KPEBERT) model by proposing a novel self-supervised contrastive learning method, which is more compatible to MDERank than vanilla BERT. Comprehensive evaluations on six KPE benchmarks demonstrate that the proposed MDERank outperforms state-of-the-art unsupervised KPE approach by average 1.80 $F1@15$ improvement. MDERank further benefits from KPEBERT and overall achieves average 3.53 $F1@15$ improvement over the SOTA SIFRank. Our code is available at \url{https://github.com/LinhanZ/mderank}.

cs.CL↗
arXiv2022

Frictionless nanohighways on crystalline surfaces

The understanding of friction at nano-scales, ruled by the regular arrangement of atoms, is surprisingly incomplete. Here we provide a unified understanding by studying the interlocking potential energy of two infinite contacting surfaces with arbitrary lattice symmetries, and extending it to finite contacts. We categorize, based purely on geometrical features, all possible contacts into three different types: a structurally lubric contact where the monolayer can move isotropically without friction, a corrugated and strongly interlocked contact, and a newly discovered directionally structurally lubric contact where the layer can move frictionlessly along one specific direction and retains finite friction along all other directions. This novel category is energetically stable against rotational perturbations and provides extreme friction anisotropy. The finite-size analysis shows that our categorization applies to a wide range of technologically relevant materials in contact, from adsorbates on crystal surfaces to layered two-dimensional materials and colloidal monolayers.

cond-mat.soft↗
arXiv2022

Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes

We study the problem of embedding edgeless nodes such as users who newly enter the underlying network, while using graph neural networks (GNNs) widely studied for effective representation learning of graphs. Our study is motivated by the fact that GNNs cannot be straightforwardly adopted for our problem since message passing to such edgeless nodes having no connections is impossible. To tackle this challenge, we propose Edgeless-GNN, a novel inductive framework that enables GNNs to generate node embeddings even for edgeless nodes through unsupervised learning. Specifically, we start by constructing a proxy graph based on the similarity of node attributes as the GNN's computation graph defined by the underlying network. The known network structure is used to train model parameters, whereas a topology-aware loss function is established in such a way that our model judiciously learns the network structure by encoding positive, negative, and second-order relations between nodes. For the edgeless nodes, we inductively infer embeddings by expanding the computation graph. By evaluating the performance of various downstream machine learning tasks, we empirically demonstrate that Edgeless-GNN exhibits (a) superiority over state-of-the-art inductive network embedding methods for edgeless nodes, (b) effectiveness of our topology-aware loss function, (c) robustness to incomplete node attributes, and (d) a linear scaling with the graph size.

cs.SI↗
arXiv2022

Improved Binary Forward Exploration: Learning Rate Scheduling Method for Stochastic Optimization

A new gradient-based optimization approach by automatically scheduling the learning rate has been proposed recently, which is called Binary Forward Exploration (BFE). The Adaptive version of BFE has also been discussed thereafter. In this paper, the improved algorithms based on them will be investigated, in order to optimize the efficiency and robustness of the new methodology. This improved approach provides a new perspective to scheduling the update of learning rate and will be compared with the stochastic gradient descent, aka SGD algorithm with momentum or Nesterov momentum and the most successful adaptive learning rate algorithm e.g. Adam. The goal of this method does not aim to beat others but provide a different viewpoint to optimize the gradient descent process. This approach combines the advantages of the first-order and second-order optimizations in the aspects of speed and efficiency.

cs.LG↗
arXiv2022

Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting

We all depend on mobility, and vehicular transportation affects the daily lives of most of us. Thus, the ability to forecast the state of traffic in a road network is an important functionality and a challenging task. Traffic data is often obtained from sensors deployed in a road network. Recent proposals on spatial-temporal graph neural networks have achieved great progress at modeling complex spatial-temporal correlations in traffic data, by modeling traffic data as a diffusion process. However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals. Unfortunately, nearly all previous works coarsely consider traffic signals entirely as the outcome of the diffusion, while neglecting the inherent signals, which impacts model performance negatively. To improve modeling performance, we propose a novel Decoupled Spatial-Temporal Framework (DSTF) that separates the diffusion and inherent traffic information in a data-driven manner, which encompasses a unique estimation gate and a residual decomposition mechanism. The separated signals can be handled subsequently by the diffusion and inherent modules separately. Further, we propose an instantiation of DSTF, Decoupled Dynamic Spatial-Temporal Graph Neural Network (D2STGNN), that captures spatial-temporal correlations and also features a dynamic graph learning module that targets the learning of the dynamic characteristics of traffic networks. Extensive experiments with four real-world traffic datasets demonstrate that the framework is capable of advancing the state-of-the-art.

cs.LG↗