arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 397 records · Page 22Linked to original sources

arXiv2023

Localization-delocalization Transition in an electromagnetically induced photonic lattice

We investigate the localization-delocalization transition (LDT) in an electromagnetically induced photonic lattice. A four-level tripod-type scheme in atomic ensembles is proposed to generate an effective photonic moiré lattice through the electromagnetically induced transparency (EIT) mechanism. By taking advantage of the tunable atomic coherence, we show that both periodic (commensurable) and aperiodic (incommensurable) structure can be created in such a photonic moiré lattice via adjusting the twist angle between two superimposed periodic patterns with square primitive. Furthermore, we also find that by tuning the amplitudes of these two superimposed periodic patterns, the localization-delocalization transition occurs for the light propagating in the aperiodic moiré lattice. Such localization is shown to link the fact that the flat bands of moiré lattice support quasi-nondiffracting localized modes and thus induce the localization of the initially localized beam. It would provide a promising approach to control the light propagation via the electromagnetically induced photonic lattice.

cond-mat.quant-gas↗

arXiv2023

Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance

Winograd is generally utilized to optimize convolution performance and computational efficiency because of the reduced multiplication operations, but the reliability issues brought by winograd are usually overlooked. In this work, we observe the great potential of winograd convolution in improving neural network (NN) fault tolerance. Based on the observation, we evaluate winograd convolution fault tolerance comprehensively from different granularities ranging from models, layers, and operation types for the first time. Then, we explore the use of inherent fault tolerance of winograd convolution for cost-effective NN protection against soft errors. Specifically, we mainly investigate how winograd convolution can be effectively incorporated with classical fault-tolerant design approaches including triple modular redundancy (TMR), fault-aware retraining, and constrained activation functions. According to our experiments, winograd convolution can reduce the fault-tolerant design overhead by 55.77\% on average without any accuracy loss compared to standard convolution, and further reduce the computing overhead by 17.24\% when the inherent fault tolerance of winograd convolution is considered. When it is applied on fault-tolerant neural networks enhanced with fault-aware retraining and constrained activation functions, the resulting model accuracy generally shows significant improvement in presence of various faults.

cs.LG↗

arXiv2023

Trusted AI in Multi-agent Systems: An Overview of Privacy and Security for Distributed Learning

Motivated by the advancing computational capacity of distributed end-user equipments (UEs), as well as the increasing concerns about sharing private data, there has been considerable recent interest in machine learning (ML) and artificial intelligence (AI) that can be processed on on distributed UEs. Specifically, in this paradigm, parts of an ML process are outsourced to multiple distributed UEs, and then the processed ML information is aggregated on a certain level at a central server, which turns a centralized ML process into a distributed one, and brings about significant benefits. However, this new distributed ML paradigm raises new risks of privacy and security issues. In this paper, we provide a survey of the emerging security and privacy risks of distributed ML from a unique perspective of information exchange levels, which are defined according to the key steps of an ML process, i.e.: i) the level of preprocessed data, ii) the level of learning models, iii) the level of extracted knowledge and, iv) the level of intermediate results. We explore and analyze the potential of threats for each information exchange level based on an overview of the current state-of-the-art attack mechanisms, and then discuss the possible defense methods against such threats. Finally, we complete the survey by providing an outlook on the challenges and possible directions for future research in this critical area.

cs.DC↗

arXiv2023

Diffusion-based Time Series Data Imputation for Microsoft 365

Reliability is extremely important for large-scale cloud systems like Microsoft 365. Cloud failures such as disk failure, node failure, etc. threaten service reliability, resulting in online service interruptions and economic loss. Existing works focus on predicting cloud failures and proactively taking action before failures happen. However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance. In this paper, we focus on enhancing data quality through data imputation by the proposed Diffusion+, a sample-efficient diffusion model, to impute the missing data efficiently based on the observed data. Our experiments and application practice show that our model contributes to improving the performance of the downstream failure prediction task.

cs.DC↗

arXiv2023

Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce

Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems. Position bias in training data biases the ranking model, leading to increasingly unfair item rankings, click-through-rate (CTR), and conversion rate (CVR) predictions. To jointly mitigate position bias in both item CTR and CVR prediction, we propose two position-bias-free CTR and CVR prediction models: Position-Aware Click-Conversion (PACC) and PACC via Position Embedding (PACC-PE). PACC is built upon probability decomposition and models position information as a probability. PACC-PE utilizes neural networks to model product-specific position information as embedding. Experiments on the E-commerce sponsored product search dataset show that our proposed models have better ranking effectiveness and can greatly alleviate position bias in both CTR and CVR prediction.

cs.IR↗

arXiv2023

Hierarchical Spatio-Temporal Representation Learning for Gait Recognition

Gait recognition is a biometric technique that identifies individuals by their unique walking styles, which is suitable for unconstrained environments and has a wide range of applications. While current methods focus on exploiting body part-based representations, they often neglect the hierarchical dependencies between local motion patterns. In this paper, we propose a hierarchical spatio-temporal representation learning (HSTL) framework for extracting gait features from coarse to fine. Our framework starts with a hierarchical clustering analysis to recover multi-level body structures from the whole body to local details. Next, an adaptive region-based motion extractor (ARME) is designed to learn region-independent motion features. The proposed HSTL then stacks multiple ARMEs in a top-down manner, with each ARME corresponding to a specific partition level of the hierarchy. An adaptive spatio-temporal pooling (ASTP) module is used to capture gait features at different levels of detail to perform hierarchical feature mapping. Finally, a frame-level temporal aggregation (FTA) module is employed to reduce redundant information in gait sequences through multi-scale temporal downsampling. Extensive experiments on CASIA-B, OUMVLP, GREW, and Gait3D datasets demonstrate that our method outperforms the state-of-the-art while maintaining a reasonable balance between model accuracy and complexity.

cs.CV↗

arXiv2023

SMTNet: Hierarchical cavitation intensity recognition based on sub-main transfer network

With the rapid development of smart manufacturing, data-driven machinery health management has been of growing attention. In situations where some classes are more difficult to be distinguished compared to others and where classes might be organised in a hierarchy of categories, current DL methods can not work well. In this study, a novel hierarchical cavitation intensity recognition framework using Sub-Main Transfer Network, termed SMTNet, is proposed to classify acoustic signals of valve cavitation. SMTNet model outputs multiple predictions ordered from coarse to fine along a network corresponding to a hierarchy of target cavitation states. Firstly, a data augmentation method based on Sliding Window with Fast Fourier Transform (Swin-FFT) is developed to solve few-shot problem. Secondly, a 1-D double hierarchical residual block (1-D DHRB) is presented to capture sensitive features of the frequency domain valve acoustic signals. Thirdly, hierarchical multi-label tree is proposed to assist the embedding of the semantic structure of target cavitation states into SMTNet. Fourthly, experience filtering mechanism is proposed to fully learn a prior knowledge of cavitation detection model. Finally, SMTNet has been evaluated on two cavitation datasets without noise (Dataset 1 and Dataset 2), and one cavitation dataset with real noise (Dataset 3) provided by SAMSON AG (Frankfurt). The prediction accurcies of SMTNet for cavitation intensity recognition are as high as 95.32%, 97.16% and 100%, respectively. At the same time, the testing accuracies of SMTNet for cavitation detection are as high as 97.02%, 97.64% and 100%. In addition, SMTNet has also been tested for different frequencies of samples and has achieved excellent results of the highest frequency of samples of mobile phones.

cs.SD↗

arXiv2023

Chiral odd Chern number lattice supersolidity with tunable unpaired Majorana fermions in a Rydberg-dressed Fermi gas

There is growing interest to search the chiral Majorana fermions that could arise as the quasi-particle edge state of a two-dimensional topological state of matter. Here we propose a new platform, i.e., a two-dimensional chiral odd Chern number lattice supersolid state, for supporting multiple number-tunable chiral Majorana fermions from a single component Rydberg-dressed Fermi gas in an optical lattice. The attractiveness of our idea rests on the fact that by introducing the unveiled competition between two distinct length scales, i.e., lattice period and the distance of resonant Rydberg-dressing, can provide a new way to manipulate the spatial dependence of both the strength and sign of the effective Rydberg-dressed interaction. Such a designed effective interaction turns out, can induce an unveiled odd Chern number lattice supersolid state, which is confirmed by both the mean-field and Monte Carlo calculations. Furthermore, we also find that the spontaneously formed density modulation resulted from the discrete translational symmetry breaking provides a natural way of tuning the system's topology arising from the superfluidity induced by the $U(1)$ symmetry breaking. It thus provide an alternative way for manipulating the chiral Majorana fermions, which would be useful in topological quantum computation.

cond-mat.quant-gas↗

arXiv2023

Benchmarking Reinforcement Learning Techniques for Autonomous Navigation

Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches lack safety guarantees; and learned navigation systems may not generalize well to unseen environments. Despite a variety of recent learning techniques to tackle these challenges in general, a lack of an open-source benchmark and reproducible learning methods specifically for autonomous navigation makes it difficult for roboticists to choose what learning methods to use for their mobile robots and for learning researchers to identify current shortcomings of general learning methods for autonomous navigation. In this paper, we identify four major desiderata of applying deep RL approaches for autonomous navigation: (D1) reasoning under uncertainty, (D2) safety, (D3) learning from limited trial-and-error data, and (D4) generalization to diverse and novel environments. Then, we explore four major classes of learning techniques with the purpose of achieving one or more of the four desiderata: memory-based neural network architectures (D1), safe RL (D2), model-based RL (D2, D3), and domain randomization (D4). By deploying these learning techniques in a new open-source large-scale navigation benchmark and real-world environments, we perform a comprehensive study aimed at establishing to what extent can these techniques achieve these desiderata for RL-based navigation systems.

cs.RO↗

arXiv2023

GaitMM: Multi-Granularity Motion Sequence Learning for Gait Recognition

Gait recognition aims to identify individual-specific walking patterns by observing the different periodic movements of each body part. However, most existing methods treat each part equally and fail to account for the data redundancy caused by the different step frequencies and sampling rates of gait sequences. In this study, we propose a multi-granularity motion representation network (GaitMM) for gait sequence learning. In GaitMM, we design a combined full-body and fine-grained sequence learning module (FFSL) to explore part-independent spatio-temporal representations. Moreover, we utilize a frame-wise compression strategy, referred to as multi-scale motion aggregation (MSMA), to capture discriminative information in the gait sequence. Experiments on two public datasets, CASIA-B and OUMVLP, show that our approach reaches state-of-the-art performances.

cs.CV↗

arXiv2023

Scalable authentication and optimal flooding in a quantum network

The global interest in quantum networks stems from the security guaranteed by the laws of physics. Deploying quantum networks means facing the challenges of scaling up the physical hardware and, more importantly, of scaling up all other network layers and optimally utilising network resources. Here we consider two related protocols, their experimental demonstrations on an 8-user quantum network test-bed, and discuss their usefulness with the aid of example use cases. First, an authentication transfer protocol to manage a fundamental limitation of quantum communication -- the need for a pre-shared key between every pair of users linked together on the quantum network. By temporarily trusting some intermediary nodes for a short period of time (<35 min in our network), we can generate and distribute these initial authentication keys with a very high level of security. Second, when end users quantify their trust in intermediary nodes, our flooding protocol can be used to improve both end-to-end communication speeds and increase security against malicious nodes.

quant-ph↗

arXiv2023

The performance of large-pitch AC-LGAD with different N+ dose

AC-Coupled LGAD (AC-LGAD) is a new 4D detector developed based on the Low Gain Avalanche Diode (LGAD) technology, which can accurately measure the time and spatial information of particles. The Institute of High Energy Physics (IHEP) designed a large-size AC-LGAD with a pitch of 2000~\SI{}{\micro\metre} and AC pad of 1000~\SI{}{\micro\metre}, and explored the effect of N+ layer dose on the spatial resolution and time resolution. The spatial resolution varied from 36~\SI{}{\micro\metre} to 16~\SI{}{\micro\metre} depending on N+ dose for a charge corresponding to about 12 minimum ionizing particles. The jitter component of the time resolution does not change significantly with different N+ doses, and it is about 15-17 ps measured by laser. The AC-LGAD with a low N+ dose has a large attenuation factor and better spatial resolution in the central region between pads. In these specific conditions, large signal attenuation factor and low noise level are beneficial to improve the spatial resolution of the AC-LGAD sensor.

physics.ins-det↗

arXiv2023

DP-Image: Differential Privacy for Image Data in Feature Space

The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public. Even though differential privacy (DP) is a widely accepted criterion that can provide a provable privacy guarantee, the application of DP on unstructured data such as images is not trivial due to the lack of a clear qualification on the meaningful difference between any two images. In this paper, for the first time, we introduce a novel notion of image-aware differential privacy, referred to as DP-image, that can protect user's personal information in images, from both human and AI adversaries. The DP-Image definition is formulated as an extended version of traditional differential privacy, considering the distance measurements between feature space vectors of images. Then we propose a mechanism to achieve DP-Image by adding noise to an image feature vector. Finally, we conduct experiments with a case study on face image privacy. Our results show that the proposed DP-Image method provides excellent DP protection on images, with a controllable distortion to faces.

cs.CR↗

arXiv2023

AdaSelection: Accelerating Deep Learning Training through Data Subsampling

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance. Our method is able to flexibly combines an arbitrary number of baseline sub-sampling methods incorporating the method-level importance and intra-method sample-level importance at each iteration. The standard practice of ad-hoc sampling often leads to continuous training with vast amounts of data from production environments. To improve the selection of data instances during forward and backward passes, we propose recording a constant amount of information per instance from these passes. We demonstrate the effectiveness of our method by testing it across various types of inputs and tasks, including the classification tasks on both image and language datasets, as well as regression tasks. Compared with industry-standard baselines, AdaSelection consistently displays superior performance.

cs.LG↗

arXiv2023

Higher-order link prediction via local information

Link prediction has been widely studied as an important research direction. Higher-order link prediction has gained especially significant attention since higher-order networks provide a more accurate description of real-world complex systems. However, higher-order networks contain more complex information than traditional pairwise networks, making the prediction of higher-order links a formidable challenging task. Recently, researchers have discovered that local features have advantages over long-range features in higher-order link prediction. Therefore, it is necessary to develop more efficient and concise higher-order link prediction algorithms based on local features. In this paper, we proposed two similarity metrics via local information, simplicial decomposition weight (SDW) and closed ratio weight (CRW), to predict possible future higher-order interactions (simplices) in simplicial networks. These two algorithms capture local higher-order information at two aspects: simplex decomposition and cliques' state (closed or open). We tested their performance in eight empirical simplicial networks, and the results show that our proposed metrics outperform other benchmarks in predicting third-order and fourth-order interactions (simplices) in most cases. In addition, we explore the robustness of the proposed algorithms, and the results suggest that the performance of these novel algorithms is advanced under different sizes of training sets.

cs.SI↗

arXiv2023

Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease

Objective: Bleeding from gastroesophageal varices (GEV) is a medical emergency associated with high mortality. We aim to construct an artificial intelligence-based model of two-dimensional shear wave elastography (2D-SWE) of the liver and spleen to precisely assess the risk of GEV and high-risk gastroesophageal varices (HRV). Design: A prospective multicenter study was conducted in patients with compensated advanced chronic liver disease. 305 patients were enrolled from 12 hospitals, and finally 265 patients were included, with 1136 liver stiffness measurement (LSM) images and 1042 spleen stiffness measurement (SSM) images generated by 2D-SWE. We leveraged deep learning methods to uncover associations between image features and patient risk, and thus conducted models to predict GEV and HRV. Results: A multi-modality Deep Learning Risk Prediction model (DLRP) was constructed to assess GEV and HRV, based on LSM and SSM images, and clinical information. Validation analysis revealed that the AUCs of DLRP were 0.91 for GEV (95% CI 0.90 to 0.93, p < 0.05) and 0.88 for HRV (95% CI 0.86 to 0.89, p < 0.01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM. Moreover, DLPR was better than the model using individual parameters, including LSM and SSM images. In HRV prediction, the 2D-SWE images of SSM outperform LSM (p < 0.01). Conclusion: DLRP shows excellent performance in predicting GEV and HRV over canonical risk indicators LSM and SSM. Additionally, the 2D-SWE images of SSM provided more information for better accuracy in predicting HRV than the LSM.

q-bio.TO↗

arXiv2023

Eta Form and Spectral Sequence for the Composition of Fibrations

In this paper, inspired by the spectral sequences constructed by signature operators with respect to the composition of fibrations, we define the "spectral sequences" for fiberwise Dirac operators and prove the equivariant family version of the adiabatic limit formula of eta invariants using the heat kernel method and the analytic localization techniques established by Bismut-Lebeau. In our formula, the remainder terms are constructed by "spectral sequences" and completely extend those of Dai and Bunke-Ma.

math.DG↗

arXiv2023

Multi-task Combinatorial Optimization: Adaptive Multi-modality Knowledge Transfer by an Explicit Inter-task Distance

Scheduling problems are often tackled independently, and rarely solved by leveraging the commonalities across problems. Lack of awareness of this inter-task similarity could impede the search efficacy. A quantifiable relationship between scheduling problems is to-date rather unclear, how to leverage it in combinatorial optimization remains largely unknown, and its effects on search are also undeterminable. This paper addresses these hard questions by delving into quantifiable useful inter-task relationships and, through leveraging the explicit relationship, presenting a speed-up algorithm. After deriving an analytical inter-task distance metric to quantitatively reveal latent similarity across scheduling problems, an adaptive transfer of multi-modality knowledge is devised to promptly adjust the transfer in forms of explicit and implicit knowledge in response to heterogeneity in the inter-task discrepancy. For faintly related problems with disappearing dependences, a problem transformation function is suggested with a matching-feature-based greedy policy, and the function projects faintly related problems into a latent space where these problems gain similarity in a way that creates search speed-ups. Finally, a multi-task scatter search combinatorial algorithm is formed and a large-scale multi-task benchmark is generated serving the purposes of validation. That the algorithm exhibits dramatic speed-ups of 2~3 orders of magnitude, as compared to direct problem solving in strongly related problems and 3 times faster in weakly related ones, suggests leveraging commonality across problems could be successful.

math.OC↗