arXiv subjects

Lin Zhang

Publications and source records attributed to Lin Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2023

Visualization of all two-qubit states via partial-transpose-moments

Efficiently detecting entanglement based on measurable quantities is a basic problem for quantum information processing. Recently, the measurable quantities called partial-transpose (PT)-moments have been proposed to detect and characterize entanglement. In the recently published paper [L. Zhang \emph{et al.}, \href{https://doi.org/10.1002/andp.202200289}{Ann. Phys.(Berlin) \textbf{534}, 2200289 (2022)}], we have already identified the 2-dimensional (2D) region, comprised of the second and third PT-moments, corresponding to two-qubit entangled states, and described the whole region for all two-qubit states. In the present paper, we visualize the 3D region corresponding to all two-qubit states by further involving the fourth PT-moment (the last one for two-qubit states). The characterization of this 3D region can finally be achieved by optimizing some polynomials. Furthermore, we identify the dividing surface which separates the two parts of the whole 3D region corresponding to entangled and separable states respectively. Due to the measurability of PT-moments, we obtain a complete and operational criterion for the detection of two-qubit entanglement.

quant-ph↗

arXiv2023

Precise late-time asymptotics of scalar field in the interior of a subextreme Kerr black hole and its application in Strong Cosmic Censorship conjecture

In this work, we compute the precise late-time asymptotics for the scalar field in the interior of a non-static subextreme Kerr black hole, based on recent progress on deriving its precise asymptotics in the Kerr exterior region. This provides a new proof of the generic $H^1_{\text{loc}}$-inextendibility of the Kerr Cauchy horizon against scalar perturbations that is first shown by Luk--Sbierski (J. Func. Anal., 2016). The analogous results in Reissner--Nordström spacetimes are also discussed.

gr-qc↗

arXiv2023

Sharp decay for Teukolsky equation in Kerr spacetimes

In this work, we derive the global sharp decay, as both a lower and an upper bounds, for the spin $\pm \mathfrak{s}$ components, which are solutions to the Teukolsky equation, in the black hole exterior and on the event horizon of a slowly rotating Kerr spacetime. These estimates are generalized to any subextreme Kerr background under an integrated local energy decay estimate. Our results apply to the scalar field $(\mathfrak{s}=0)$, the Maxwell field $(\mathfrak{s}=1)$ and the linearized gravity $(\mathfrak{s}=2)$ and confirm the Price's law decay that is conjectured to be sharp. Our analyses rely on a novel global conservation law for the Teukolsky equation, and this new approach can be applied to derive the precise asymptotics for solutions to semilinear wave equations.

gr-qc↗

arXiv2023

Price's law for spin fields on a Schwarzschild background

In this work, we derive the globally precise late-time asymptotics for the spin-$\mathfrak{s}$ fields on a Schwarzschild background, including the scalar field $(\mathfrak{s}=0)$, the Maxwell field $(\mathfrak{s}=\pm 1)$ and the linearized gravity $(\mathfrak{s}=\pm 2)$. The conjectured Price's law in the physics literature which predicts the sharp rates of decay of the spin $s=\pm \mathfrak{s}$ components towards the future null infinity as well as in a compact region is shown. Further, we confirm the heuristic claim by Barack and Ori that the spin $+1, +2$ components have an extra power of decay at the event horizon than the conjectured Price's law. The asymptotics are derived via a unified, detailed analysis of the Teukolsky master equation that is satisfied by all these components.

math.AP↗

arXiv2023

Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks

Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training. With the randomly-initialized weights, we can then seek the optimal architecture parameters via the sparse coding objective and derive a novel NAS-GNNs method, namely neural architecture coding (NAC). Consequently, our NAC holds a no-update scheme on GNNs and can efficiently compute in linear time. Empirical evaluations on multiple GNN benchmark datasets demonstrate that our approach leads to state-of-the-art performance, which is up to $200\times$ faster and $18.8\%$ more accurate than the strong baselines.

cs.LG↗

arXiv2023

DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining

Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations. This has been commonly adopted in popular distributed deep learning frameworks. However, there exist two fundamental problems: (1) excessive startup latency proportional to the number of workers for each all-reduce operation; (2) it only achieves sub-optimal training performance due to the dependency and synchronization requirement of the feed-forward computation in the next iteration. We propose a novel scheduling algorithm, DeAR, that decouples the all-reduce primitive into two continuous operations, which overlaps with both backpropagation and feed-forward computations without extra communications. We further design a practical tensor fusion algorithm to improve the training performance. Experimental results with five popular models show that DeAR achieves up to 83% and 15% training speedup over the state-of-the-art solutions on a 64-GPU cluster with 10Gb/s Ethernet and 100Gb/s InfiniBand interconnects, respectively.

cs.LG↗

arXiv2023

Evaluation and Optimization of Gradient Compression for Distributed Deep Learning

To accelerate distributed training, many gradient compression methods have been proposed to alleviate the communication bottleneck in synchronous stochastic gradient descent (S-SGD), but their efficacy in real-world applications still remains unclear. In this work, we first evaluate the efficiency of three representative compression methods (quantization with Sign-SGD, sparsification with Top-k SGD, and low-rank with Power-SGD) on a 32-GPU cluster. The results show that they cannot always outperform well-optimized S-SGD or even worse due to their incompatibility with three key system optimization techniques (all-reduce, pipelining, and tensor fusion) in S-SGD. To this end, we propose a novel gradient compression method, called alternate compressed Power-SGD (ACP-SGD), which alternately compresses and communicates low-rank matrices. ACP-SGD not only significantly reduces the communication volume, but also enjoys the three system optimizations like S-SGD. Compared with Power-SGD, the optimized ACP-SGD can largely reduce the compression and communication overheads, while achieving similar model accuracy. In our experiments, ACP-SGD achieves an average of 4.06x and 1.43x speedups over S-SGD and Power-SGD, respectively, and it consistently outperforms other baselines across different setups (from 8 GPUs to 64 GPUs and from 1Gb/s Ethernet to 100Gb/s InfiniBand).

cs.LG↗

arXiv2023

D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching

Subgraph matching is a fundamental building block for graph-based applications and is challenging due to its high-order combinatorial nature. Existing studies usually tackle it by combinatorial optimization or learning-based methods. However, they suffer from exponential computational costs or searching the matching without theoretical guarantees. In this paper, we develop D2Match by leveraging the efficiency of Deep learning and Degeneracy for subgraph matching. More specifically, we first prove that subgraph matching can degenerate to subtree matching, and subsequently is equivalent to finding a perfect matching on a bipartite graph. We can then yield an implementation of linear time complexity by the built-in tree-structured aggregation mechanism on graph neural networks. Moreover, circle structures and node attributes can be easily incorporated in D2Match to boost the matching performance. Finally, we conduct extensive experiments to show the superior performance of our D2Match and confirm that our D2Match indeed exploits the subtrees and differs from existing GNNs-based subgraph matching methods that depend on memorizing the data distribution divergence

cs.LG↗

arXiv2023

Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle Pursuit

Multi-vehicle pursuit (MVP) such as autonomous police vehicles pursuing suspects is important but very challenging due to its mission and safety critical nature. While multi-agent reinforcement learning (MARL) algorithms have been proposed for MVP problem in structured grid-pattern roads, the existing algorithms use randomly training samples in centralized learning, which leads to homogeneous agents showing low collaboration performance. For the more challenging problem of pursuing multiple evading vehicles, these algorithms typically select a fixed target evading vehicle for pursuing vehicles without considering dynamic traffic situation, which significantly reduces pursuing success rate. To address the above problems, this paper proposes a Progression Cognition Reinforcement Learning with Prioritized Experience for MVP (PEPCRL-MVP) in urban multi-intersection dynamic traffic scenes. PEPCRL-MVP uses a prioritization network to assess the transitions in the global experience replay buffer according to the parameters of each MARL agent. With the personalized and prioritized experience set selected via the prioritization network, diversity is introduced to the learning process of MARL, which can improve collaboration and task related performance. Furthermore, PEPCRL-MVP employs an attention module to extract critical features from complex urban traffic environments. These features are used to develop progression cognition method to adaptively group pursuing vehicles. Each group efficiently target one evading vehicle in dynamic driving environments. Extensive experiments conducted with a simulator over unstructured roads of an urban area show that PEPCRL-MVP is superior to other state-of-the-art methods. Specifically, PEPCRL-MVP improves pursuing efficiency by 3.95% over TD3-DMAP and its success rate is 34.78% higher than that of MADDPG. Codes are open sourced.

cs.AI↗

arXiv2023

Range-Based Equal Error Rate for Spoof Localization

Spoof localization, also called segment-level detection, is a crucial task that aims to locate spoofs in partially spoofed audio. The equal error rate (EER) is widely used to measure performance for such biometric scenarios. Although EER is the only threshold-free metric, it is usually calculated in a point-based way that uses scores and references with a pre-defined temporal resolution and counts the number of misclassified segments. Such point-based measurement overly relies on this resolution and may not accurately measure misclassified ranges. To properly measure misclassified ranges and better evaluate spoof localization performance, we upgrade point-based EER to range-based EER. Then, we adapt the binary search algorithm for calculating range-based EER and compare it with the classical point-based EER. Our analyses suggest utilizing either range-based EER, or point-based EER with a proper temporal resolution can fairly and properly evaluate the performance of spoof localization.

cs.SD↗

arXiv2023

Feature Expansion for Graph Neural Networks

Graph neural networks aim to learn representations for graph-structured data and show impressive performance, particularly in node classification. Recently, many methods have studied the representations of GNNs from the perspective of optimization goals and spectral graph theory. However, the feature space that dominates representation learning has not been systematically studied in graph neural networks. In this paper, we propose to fill this gap by analyzing the feature space of both spatial and spectral models. We decompose graph neural networks into determined feature spaces and trainable weights, providing the convenience of studying the feature space explicitly using matrix space analysis. In particular, we theoretically find that the feature space tends to be linearly correlated due to repeated aggregations. Motivated by these findings, we propose 1) feature subspaces flattening and 2) structural principal components to expand the feature space. Extensive experiments verify the effectiveness of our proposed more comprehensive feature space, with comparable inference time to the baseline, and demonstrate its efficient convergence capability.

cs.LG↗

arXiv2023

A Diffusion Model for Event Skeleton Generation

Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task. Existing methods effectively address this task from a graph generation perspective but suffer from noise-sensitive and error accumulation, e.g., the inability to correct errors while generating schema. We, therefore, propose a novel Diffusion Event Graph Model~(DEGM) to address these issues. Our DEGM is the first workable diffusion model for event skeleton generation, where the embedding and rounding techniques with a custom edge-based loss are introduced to transform a discrete event graph into learnable latent representation. Furthermore, we propose a denoising training process to maintain the model's robustness. Consequently, DEGM derives the final schema, where error correction is guaranteed by iteratively refining the latent representation during the schema generation process. Experimental results on three IED bombing datasets demonstrate that our DEGM achieves better results than other state-of-the-art baselines. Our code and data are available at https://github.com/zhufq00/EventSkeletonGeneration.

cs.CL↗

arXiv2023

Margin-closed vector autoregressive time series models

Conditions are obtained for a Gaussian vector autoregressive time series of order $k$, VAR($k$), to have univariate margins that are autoregressive of order $k$ or lower-dimensional margins that are also VAR($k$). This can lead to $d$-dimensional VAR($k$) models that are closed with respect to a given partition $\{S_1,\ldots,S_n\}$ of $\{1,\ldots,d\}$ by specifying marginal serial dependence and some cross-sectional dependence parameters. The special closure property allows one to fit the sub-processes of multivariate time series before assembling them by fitting the dependence structure between the sub-processes. We revisit the use of the Gaussian copula of the stationary joint distribution of observations in the VAR($k$) process with non-Gaussian univariate margins but under the constraint of closure under margins. This construction allows more flexibility in handling higher-dimensional time series and a multi-stage estimation procedure can be used. The proposed class of models is applied to a macro-economic data set and compared with the relevant benchmark models.

stat.ME↗

arXiv2023

Improving Your Graph Neural Networks: A High-Frequency Booster

Graph neural networks (GNNs) hold the promise of learning efficient representations of graph-structured data, and one of its most important applications is semi-supervised node classification. However, in this application, GNN frameworks tend to fail due to the following issues: over-smoothing and heterophily. The most popular GNNs are known to be focused on the message-passing framework, and recent research shows that these GNNs are often bounded by low-pass filters from a signal processing perspective. We thus incorporate high-frequency information into GNNs to alleviate this genetic problem. In this paper, we argue that the complement of the original graph incorporates a high-pass filter and propose Complement Laplacian Regularization (CLAR) for an efficient enhancement of high-frequency components. The experimental results demonstrate that CLAR helps GNNs tackle over-smoothing, improving the expressiveness of heterophilic graphs, which adds up to 3.6% improvement over popular baselines and ensures topological robustness.

cs.LG↗

arXiv2023

HybridCVLNet: A Hybrid CSI Feedback System and its Domain Adaptation

Deep Learning (DL)-based channel state information (CSI) feedback is a promising technique for the transmitter to accurately acquire the CSI of massive multiple-input multiple-output (MIMO) systems. As critical concerns about DL-based physical layer applications, the intra-domain generalizability affected by dataset bias and inter-domain robustness in data drift remain challenging. Therefore, we build on a Hybrid Complex-Valued Lightweight framework, namely the HybridCVLNet, capable of overcoming the dataset bias with regularized hybrid structure and codeword. Meanwhile, a corresponding transductive-based hybrid domain adaptation scheme is proposed to tackle the inter-domain data drift. The experiment verifies that HybridCVLNet achieves stable generalizability and performance gain over the state-of-the-art (SOTA) feedback schemes in an intra-domain heterogeneous dataset. In addition, its transductive-based hybrid domain adaptation scheme is more efficient and superior to the inductive-based transfer learning methods under two inter-domain online re-optimization settings.

eess.SP↗

arXiv2023

Detection of Pavement Cracks by Deep Learning Models of Transformer and UNet

Fracture is one of the main failure modes of engineering structures such as buildings and roads. Effective detection of surface cracks is significant for damage evaluation and structure maintenance. In recent years, the emergence and development of deep learning techniques have shown great potential to facilitate surface crack detection. Currently, most reported tasks were performed by a convolutional neural network (CNN), while the limitation of CNN may be improved by the transformer architecture introduced recently. In this study, we investigated nine promising models to evaluate their performance in pavement surface crack detection by model accuracy, computational complexity, and model stability. We created 711 images of 224 by 224 pixels with crack labels, selected an optimal loss function, compared the evaluation metrics of the validation dataset and test dataset, analyzed the data details, and checked the segmentation outcomes of each model. We find that transformer-based models generally are easier to converge during the training process and have higher accuracy, but usually exhibit more memory consumption and low processing efficiency. Among nine models, SwinUNet outperforms the other two transformers and shows the highest accuracy among nine models. The results should shed light on surface crack detection by various deep-learning models and provide a guideline for future applications in this field.

cs.CV↗

arXiv2023

Unified characterization for higher-order topological phase transitions

Higher-order topological phase transitions (HOTPTs) are associated with closing either the bulk energy gap (type-I) or boundary energy gap (type-II) without changing symmetry, and conventionally the both transitions are captured in real space and characterized separately. Here we propose a momentum-space topological characterization of the HOTPTs, which unifies the both types of topological transitions and enables a precise detection by quench dynamics. Our unified characterization is based on a novel correspondence between the mass domain walls on real-space boundaries and the higher-order band-inversion surfaces (BIS) which are characteristic interfaces in the momentum subspace. The topological transitions occur when momentum-space topological nodes, dubbed higher-order topological charges, cross the higher-order BISs after proper projection. Particularly, the bulk (boundary) gap closes when all (part of) topological charges cross the BISs, characterizing the type-I (type-II) HOTPTs. These distinct dynamical behaviours of higher-order topological charges can be feasibly measured from quench dynamics driven with control in experiments. Our work opens an avenue to characterize and detect the two types of HOTPTs within a unified framework, and shall advance the research in both theory and experiment.

cond-mat.mes-hall↗

arXiv2023

Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence

Nowadays, foundation models become one of fundamental infrastructures in artificial intelligence, paving ways to the general intelligence. However, the reality presents two urgent challenges: existing foundation models are dominated by the English-language community; users are often given limited resources and thus cannot always use foundation models. To support the development of the Chinese-language community, we introduce an open-source project, called Fengshenbang, which leads by the research center for Cognitive Computing and Natural Language (CCNL). Our project has comprehensive capabilities, including large pre-trained models, user-friendly APIs, benchmarks, datasets, and others. We wrap all these in three sub-projects: the Fengshenbang Model, the Fengshen Framework, and the Fengshen Benchmark. An open-source roadmap, Fengshenbang, aims to re-evaluate the open-source community of Chinese pre-trained large-scale models, prompting the development of the entire Chinese large-scale model community. We also want to build a user-centered open-source ecosystem to allow individuals to access the desired models to match their computing resources. Furthermore, we invite companies, colleges, and research institutions to collaborate with us to build the large-scale open-source model-based ecosystem. We hope that this project will be the foundation of Chinese cognitive intelligence.

cs.CL↗