arXiv subjects

Jin Li

Publications and source records attributed to Jin Li.

At least 181 records · Page 10Linked to original sources

arXiv2023

Two-stage MR Image Segmentation Method for Brain Tumors based on Attention Mechanism

Multimodal magnetic resonance imaging (MRI) can reveal different patterns of human tissue and is crucial for clinical diagnosis. However, limited by cost, noise and manual labeling, obtaining diverse and reliable multimodal MR images remains a challenge. For the same lesion, different MRI manifestations have great differences in background information, coarse positioning and fine structure. In order to obtain better generation and segmentation performance, a coordination-spatial attention generation adversarial network (CASP-GAN) based on the cycle-consistent generative adversarial network (CycleGAN) is proposed. The performance of the generator is optimized by introducing the Coordinate Attention (CA) module and the Spatial Attention (SA) module. The two modules can make full use of the captured location information, accurately locating the interested region, and enhancing the generator model network structure. The ability to extract the structure information and the detailed information of the original medical image can help generate the desired image with higher quality. There exist some problems in the original CycleGAN that the training time is long, the parameter amount is too large, and it is difficult to converge. In response to this problem, we introduce the Coordinate Attention (CA) module to replace the Res Block to reduce the number of parameters, and cooperate with the spatial information extraction network above to strengthen the information extraction ability. On the basis of CASP-GAN, an attentional generative cross-modality segmentation (AGCMS) method is further proposed. This method inputs the modalities generated by CASP-GAN and the real modalities into the segmentation network for brain tumor segmentation. Experimental results show that CASP-GAN outperforms CycleGAN and some state-of-the-art methods in PSNR, SSMI and RMSE in most tasks.

eess.IV↗

arXiv2023

Dynamic Selection in Algorithmic Decision-making

This paper identifies and addresses dynamic selection problems in online learning algorithms with endogenous data. In a contextual multi-armed bandit model, a novel bias (self-fulfilling bias) arises because the endogeneity of the data influences the choices of decisions, affecting the distribution of future data to be collected and analyzed. We propose an instrumental-variable-based algorithm to correct for the bias. It obtains true parameter values and attains low (logarithmic-like) regret levels. We also prove a central limit theorem for statistical inference. To establish the theoretical properties, we develop a general technique that untangles the interdependence between data and actions.

econ.EM↗

arXiv2023

Autoencoder-based Anomaly Detection in Streaming Data with Incremental Learning and Concept Drift Adaptation

In our digital universe nowadays, enormous amount of data are produced in a streaming manner in a variety of application areas. These data are often unlabelled. In this case, identifying infrequent events, such as anomalies, poses a great challenge. This problem becomes even more difficult in non-stationary environments, which can cause deterioration of the predictive performance of a model. To address the above challenges, the paper proposes an autoencoder-based incremental learning method with drift detection (strAEm++DD). Our proposed method strAEm++DD leverages on the advantages of both incremental learning and drift detection. We conduct an experimental study using real-world and synthetic datasets with severe or extreme class imbalance, and provide an empirical analysis of strAEm++DD. We further conduct a comparative study, showing that the proposed method significantly outperforms existing baseline and advanced methods.

cs.LG↗

arXiv2023

Vertical Ferroelectricity in Van der Waals Materials: Models and Devices

Ferroelectricity has a wide range of applications in functional electronics and is extremely important for the development of next-generation information storage technology, but it is difficult to achieve due to its special symmetry requirements. In this letter, based on van derWaals stacking, a generic model is proposed for realizing ferroelectric devices, where a freely movable center layer is packaged in two fixed and symmetrically stacked layers. In this model, the ferroelectric phase transition can be realized between the two equivalent and eccentric ground stacking-states with opposite polarizations. By means of first-principles calculations, taking the h-BN/h-BN/h-BN and h-BN/Graphene/h-BN as feasible models, we carefully evaluate the magnitude of ferroelectricity. The corresponding polarizations are estimated as 1.83 and 1.35 pC/m, respectively, which are comparable to the sliding ferroelectricity. Such a new tri-layer model of vertical ferroelectricity can be constructed by arbitrary van derWaals semiconducting materials, and usually holds low switching barrier. Optimized material combinations with remarkable polarization are highly expectable to be discovered from the huge candidate set for future information storage.

cond-mat.mtrl-sci↗

arXiv2023

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised pre-training excel at capturing longer-range global patterns and enabling better feature discrimination, while MIM can introduce more local and diverse attention across all transformer layers. In this paper, we explore how to obtain a model that combines their strengths. We start by examining previous feature distillation and mask feature reconstruction methods and identify their limitations. We find that their increasing diversity mainly derives from the asymmetric designs, but these designs may in turn compromise the discrimination ability. In order to better obtain both discrimination and diversity, we propose a simple but effective Hybrid Distillation strategy, which utilizes both the supervised/CL teacher and the MIM teacher to jointly guide the student model. Hybrid Distill imitates the token relations of the MIM teacher to alleviate attention collapse, as well as distills the feature maps of the supervised/CL teacher to enable discrimination. Furthermore, a progressive redundant token masking strategy is also utilized to reduce the distilling costs and avoid falling into local optima. Experiment results prove that Hybrid Distill can achieve superior performance on different benchmarks.

cs.CV↗

arXiv2023

G-STO: Sequential Main Shopping Intention Detection via Graph-Regularized Stochastic Transformer

Sequential recommendation requires understanding the dynamic patterns of users' behaviors, contexts, and preferences from their historical interactions. Most existing works focus on modeling user-item interactions only from the item level, ignoring that they are driven by latent shopping intentions (e.g., ballpoint pens, miniatures, etc). The detection of the underlying shopping intentions of users based on their historical interactions is a crucial aspect for e-commerce platforms, such as Amazon, to enhance the convenience and efficiency of their customers' shopping experiences. Despite its significance, the area of main shopping intention detection remains under-investigated in the academic literature. To fill this gap, we propose a graph-regularized stochastic Transformer method, G-STO. By considering intentions as sets of products and user preferences as compositions of intentions, we model both of them as stochastic Gaussian embeddings in the latent representation space. Instead of training the stochastic representations from scratch, we develop a global intention relational graph as prior knowledge for regularization, allowing relevant shopping intentions to be distributionally close. Finally, we feed the newly regularized stochastic embeddings into Transformer-based models to encode sequential information from the intention transitions. We evaluate our main shopping intention identification model on three different real-world datasets, where G-STO achieves significantly superior performances to the baselines by 18.08% in Hit@1, 7.01% in Hit@10, and 6.11% in NDCG@10 on average.

cs.IR↗

arXiv2023

Using entropy bounds to avoid the cosmological singularity and constrain cosmological particle production

In this work, we study the applications of entropy bounds in two toy cosmological models with particle production (annihilation), i.e., a radiation-dominated universe and a dust-dominated universe. We consider the co-moving volume and the volume covered by the particle horizon of a given observer as the thermodynamic systems satisfying entropy bounds. For the Bekenstein bound and the spherical entropy bound, it is found that the cosmological singularity can be avoided and cosmological particle production needs to be truncated in some special cases. Our study can be extended to other cosmological models with particle production.

astro-ph.CO↗

arXiv2023

Text Is All You Need: Learning Language Representations for Sequential Recommendation

Sequential recommendation aims to model dynamic user behavior from historical interactions. Existing methods rely on either explicit item IDs or general textual features for sequence modeling to understand user preferences. While promising, these approaches still struggle to model cold-start items or transfer knowledge to new datasets. In this paper, we propose to model user preferences and item features as language representations that can be generalized to new items and datasets. To this end, we present a novel framework, named Recformer, which effectively learns language representations for sequential recommendation. Specifically, we propose to formulate an item as a "sentence" (word sequence) by flattening item key-value attributes described by text so that an item sequence for a user becomes a sequence of sentences. For recommendation, Recformer is trained to understand the "sentence" sequence and retrieve the next "sentence". To encode item sequences, we design a bi-directional Transformer similar to the model Longformer but with different embedding layers for sequential recommendation. For effective representation learning, we propose novel pretraining and finetuning methods which combine language understanding and recommendation tasks. Therefore, Recformer can effectively recommend the next item based on language representations. Extensive experiments conducted on six datasets demonstrate the effectiveness of Recformer for sequential recommendation, especially in low-resource and cold-start settings.

cs.IR↗

arXiv2023

Learning to Personalize Recommendation based on Customers' Shopping Intents

Understanding the customers' high level shopping intent, such as their desire to go camping or hold a birthday party, is critically important for an E-commerce platform; it can help boost the quality of shopping experience by enabling provision of more relevant, explainable, and diversified recommendations. However, such high level shopping intent has been overlooked in the industry due to practical challenges. In this work, we introduce Amazon's new system that explicitly identifies and utilizes each customer's high level shopping intents for personalizing recommendations. We develop a novel technique that automatically identifies various high level goals being pursued by the Amazon customers, such as "go camping", and "preparing for a beach party". Our solution is in a scalable fashion (in 14 languages across 21 countries). Then a deep learning model maps each customer's online behavior, e.g. product search and individual item engagements, into a subset of high level shopping intents. Finally, a realtime ranker considers both the identified intents as well as the granular engagements to present personalized intent-aware recommendations. Extensive offline analysis ensures accuracy and relevance of the new recommendations and we further observe an 10% improvement in the business metrics. This system is currently serving online traffic at amazon.com, powering several production features, driving significant business impacts

cs.IR↗

arXiv2023

Atom-referenced on-chip soliton microcomb

For the applications of the frequency comb in microresonators, it is essential to obtain a fully frequency-stabilized microcomb laser source. Here, we demonstrate an atom-referenced stabilized soliton microcomb generation system based on the integrated microring resonator. The pump light around $1560.48\,\mathrm{nm}$ locked to an ultra-low-expansion (ULE) cavity, is frequency-doubled and referenced to the atomic transition of $^{87}\mathrm{Rb}$. The repetition rate of the soliton microcomb is injection-locked to an atomic-clock-stabilized radio frequency (RF) source, leading to mHz stabilization at $1$ seconds. As a result, all comb lines have been frequency-stabilized based on the atomic reference and could be determined with very high precision reaching $\sim18\,\mathrm{Hz}$ at 1 second, corresponding to the frequency stability of $9.5\times10^{-14}$. Our approach provides an integrated and fully stabilized microcomb experiment scheme with no requirement of $f-2f$ technique, which could be easily implemented and generalized to various photonic platforms, thus paving the way towards the portable and ultraprecise optical sources for high precision spectroscopy.

physics.optics↗

arXiv2023

MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction

High-accuracy, high-efficiency physics-based fluid-solid interaction is essential for reality modeling and computer animation in online games or real-time Virtual Reality (VR) systems. However, the large-scale simulation of incompressible fluid and its interaction with the surrounding solid environment is either time-consuming or suffering from the reduced time/space resolution due to the complicated iterative nature pertinent to numerical computations of involved Partial Differential Equations (PDEs). In recent years, we have witnessed significant growth in exploring a different, alternative data-driven approach to addressing some of the existing technical challenges in conventional model-centric graphics and animation methods. This paper showcases some of our exploratory efforts in this direction. One technical concern of our research is to address the central key challenge of how to best construct the numerical solver effectively and how to best integrate spatiotemporal/dimensional neural networks with the available MPM's pressure solvers.

cs.GR↗

arXiv2023

Differentially Private Numerical Vector Analyses in the Local and Shuffle Model

Numerical vector aggregation plays a crucial role in privacy-sensitive applications, such as distributed gradient estimation in federated learning and statistical analysis of key-value data. In the context of local differential privacy, this study provides a tight minimax error bound of $O(\frac{ds}{nε^2})$, where $d$ represents the dimension of the numerical vector and $s$ denotes the number of non-zero entries. By converting the conditional/unconditional numerical mean estimation problem into a frequency estimation problem, we develop an optimal and efficient mechanism called Collision. In contrast, existing methods exhibit sub-optimal error rates of $O(\frac{d^2}{nε^2})$ or $O(\frac{ds^2}{nε^2})$. Specifically, for unconditional mean estimation, we leverage the negative correlation between two frequencies in each dimension and propose the CoCo mechanism, which further reduces estimation errors for mean values compared to Collision. Moreover, to surpass the error barrier in local privacy, we examine privacy amplification in the shuffle model for the proposed mechanisms and derive precisely tight amplification bounds. Our experiments validate and compare our mechanisms with existing approaches, demonstrating significant error reductions for frequency estimation and mean estimation on numerical vectors.

cs.CR↗

arXiv2023

Fine-grained Private Knowledge Distillation

Knowledge distillation has emerged as a scalable and effective way for privacy-preserving machine learning. One remaining drawback is that it consumes privacy in a model-level (i.e., client-level) manner, every distillation query incurs privacy loss of one client's all records. In order to attain fine-grained privacy accountant and improve utility, this work proposes a model-free reverse $k$-NN labeling method towards record-level private knowledge distillation, where each record is employed for labeling at most $k$ queries. Theoretically, we provide bounds of labeling error rate under the centralized/local/shuffle model of differential privacy (w.r.t. the number of records per query, privacy budgets). Experimentally, we demonstrate that it achieves new state-of-the-art accuracy with one order of magnitude lower of privacy loss. Specifically, on the CIFAR-$10$ dataset, it reaches $82.1\%$ test accuracy with centralized privacy budget $1.0$; on the MNIST/SVHN dataset, it reaches $99.1\%$/$95.6\%$ accuracy respectively with budget $0.1$. It is the first time deep learning with differential privacy achieve comparable accuracy with reasonable data privacy protection (i.e., $\exp(ε)\leq 1.5$). Our code is available at https://github.com/liyuntong9/rknn.

cs.CR↗

arXiv2023

On statistical fluctuations in collective flows

In relativistic heavy-ion collisions, event-by-event fluctuations are known to have non-trivial implications. Even though the probability distribution is geometrically isotropic for the initial conditions, the anisotropic $\varepsilon_n$ still differs from zero owing to the statistical fluctuations in the energy profile. On the other hand, the flow harmonics extracted from the hadron spectrum using the multi-particle correlators are inevitably subjected to non-vanishing variance due to the finite number of hadrons emitted in individual events. As one aims to extract information on the fluctuations in the initial conditions via flow harmonics and their fluctuations, finite multiplicity may play a role in interfering with such an effort. In this study, we explore the properties and impacts of such fluctuations in the initial and final states, which both notably appear to be statistical ones originating from the finite number of quanta of the underlying system. We elaborate on the properties of the initial-state eccentricities for the smooth and event-by-event fluctuating initial conditions and their distinct impacts on the resulting flow harmonics. Numerical simulations are performed. The possible implications of the present study are also addressed.

nucl-th↗

arXiv2023

Differential Aggregation against General Colluding Attackers

Local Differential Privacy (LDP) is now widely adopted in large-scale systems to collect and analyze sensitive data while preserving users' privacy. However, almost all LDP protocols rely on a semi-trust model where users are curious-but-honest, which rarely holds in real-world scenarios. Recent works show poor estimation accuracy of many LDP protocols under malicious threat models. Although a few works have proposed some countermeasures to address these attacks, they all require prior knowledge of either the attacking pattern or the poison value distribution, which is impractical as they can be easily evaded by the attackers. In this paper, we adopt a general opportunistic-and-colluding threat model and propose a multi-group Differential Aggregation Protocol (DAP) to improve the accuracy of mean estimation under LDP. Different from all existing works that detect poison values on individual basis, DAP mitigates the overall impact of poison values on the estimated mean. It relies on a new probing mechanism EMF (i.e., Expectation-Maximization Filter) to estimate features of the attackers. In addition to EMF, DAP also consists of two EMF post-processing procedures (EMF* and CEMF*), and a group-wise mean aggregation scheme to optimize the final estimated mean to achieve the smallest variance. Extensive experimental results on both synthetic and real-world datasets demonstrate the superior performance of DAP over state-of-the-art solutions.

cs.CR↗

arXiv2023

Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applications

The recent availability of electronic health records (EHRs) have provided enormous opportunities to develop artificial intelligence (AI) algorithms. However, patient privacy has become a major concern that limits data sharing across hospital settings and subsequently hinders the advances in AI. Synthetic data, which benefits from the development and proliferation of generative models, has served as a promising substitute for real patient EHR data. However, the current generative models are limited as they only generate single type of clinical data for a synthetic patient, i.e., either continuous-valued or discrete-valued. To mimic the nature of clinical decision-making which encompasses various data types/sources, in this study, we propose a generative adversarial network (GAN) entitled EHR-M-GAN which simultaneously synthesizes mixed-type timeseries EHR data. EHR-M-GAN is capable of capturing the multidimensional, heterogeneous, and correlated temporal dynamics in patient trajectories. We have validated EHR-M-GAN on three publicly-available intensive care unit databases with records from a total of 141,488 unique patients, and performed privacy risk evaluation of the proposed model. EHR-M-GAN has demonstrated its superiority over state-of-the-art benchmarks for synthesizing clinical timeseries with high fidelity, while addressing the limitations regarding data types and dimensionality in the current generative models. Notably, prediction models for outcomes of intensive care performed significantly better when training data was augmented with the addition of EHR-M-GAN-generated timeseries. EHR-M-GAN may have use in developing AI algorithms in resource-limited settings, lowering the barrier for data acquisition while preserving patient privacy.

cs.LG↗

arXiv2023

Shadow thermodynamics of the Hayward-AdS black hole

In this paper, the phase structure of the Hayward-AdS black hole (BH) is studied using shadow formalism. It has been found that the shadow radius is a monotonic function of the horizon radius and can therefore play an equivalent role to the horizon radius in characterizing the thermodynamics of Hayward-AdS BH. The thermodynamic phase transition (PT) of the Hayward-AdS BH is investigated with the shadow radius. It is shown that as the magnetic charge increases, the shadow radius becomes larger, while the coexistence temperature becomes lower. The thermal profile of the Hayward-AdS BH is established by combining the temperature diagram and the shadow cast diagram, which shows that for a fixed magnetic charge, the temperature of the Hayward-AdS BH increases with the pressure while the region of the thermal profile decreases with the pressure. In particular, the temperature of the Hayward-AdS BH follows an N-type change trend when it is smaller than the critical temperature. This imply that the BH shadow may be used to investigate the thermodynamics of the Hayward-AdS BH.

gr-qc↗

arXiv2023

A Framework for Mutual Information-based MIMO Integrated Sensing and Communication Beamforming Design

Integrated sensing and communication (ISAC) unifies sensing and communication, and improves the efficiency of the spectrum, energy, and hardware. In this work, we investigate the ISAC beamforming design to maximize the mutual information between the target response matrix of a point radar target and the echo signals, while ensuring the data rate requirements of the communication users. In order to study the impact of the echo interference caused by communication users on sensing performance, we study two scenarios: a single communication user and multiple communication users. For the case of a single communication user, we consider three types of echo interference, no interference, a point interference, and an extended interference. For the case of multiple communication users, the interference is also an extended one, and furthermore, each user's communication rate requirement needs to be satisfied. To find the optimal beamforming design in these problems, we provide a closed-form solution with low complexiy, a semidefinite relaxation (SDR) method, a low-complexity algorithm based on the Majorization-Minimization (MM) method and the successive convex approximation (SCA) method, and an algorithm based on MM method and SCA method, respectively. Numerical results demonstrate that, compared to the ISAC beamforming schemes based on the Cramér-Rao bound (CRB) metric and the beampattern metric, the proposed mutual information metric can bring better beampattern and root mean square error (RMSE) of angle estimation. Furthermore, our proposed schemes designed based on the mutual information metric can suppress the echo interference from the communication users effectively.

eess.SP↗