arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 829 records · Page 46Linked to original sources

arXiv2023

POSGen: Personalized Opening Sentence Generation for Online Insurance Sales

The insurance industry is shifting their sales mode from offline to online, in expectation to reach massive potential customers in the digitization era. Due to the complexity and the nature of insurance products, a cost-effective online sales solution is to exploit chatbot AI to raise customers' attention and pass those with interests to human agents for further sales. For high response and conversion rates of customers, it is crucial for the chatbot to initiate a conversation with personalized opening sentences, which are generated with user-specific topic selection and ordering. Such personalized opening sentence generation is challenging because (i) there are limited historical samples for conversation topic recommendation in online insurance sales and (ii) existing text generation schemes often fail to support customized topic ordering based on user preferences. We design POSGen, a personalized opening sentence generation scheme dedicated for online insurance sales. It transfers user embeddings learned from auxiliary online user behaviours to enhance conversation topic recommendation, and exploits a context management unit to arrange the recommended topics in user-specific ordering for opening sentence generation. POSGen is deployed on a real-world online insurance platform. It achieves 2.33x total insurance premium improvement through a two-month global test.

cs.CL↗

arXiv2023

Direct observation of geometric and sliding ferroelectricity in an amphidynamic crystal

Sliding ferroelectricity is a recently observed polarity existing in two-dimensional materials. However, due to their weak polarization and poor electrical insulation in these materials, all available experimental evidence till now are indirect, with most based on transport properties in the nanoscale or piezoresponse force microscopy. We report the direct observation of sliding ferroelectricity, using a high-quality amphidynamic single crystal, (15-Crown-5)Cd$_3$Cl$_6$, which possesses a large band-gap and so allows direct measurement of P-E hysteresis. This coordination polymer is a van der Waals material, which is composed of inorganic stators and organic rotators as measured using XRD and NMR characterisation. From DFT calculations, we find that after the freezing of rotators an electric dipole is generated in each layer driven by the geometric mechanism, meanwhile a comparable ferroelectric polarization originates from the interlayer sliding. The net polarization of these two components can be directly measured and manipulated. Our finding provides insight into low-dimensional ferroelectrics, especially the controlling of synchronous dynamics of rotating molecules and sliding layers in solids.

cond-mat.mtrl-sci↗

arXiv2023

Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion

When upgrading neural models to a newer version, new errors that were not encountered in the legacy version can be introduced, known as regression errors. This inconsistent behavior during model upgrade often outweighs the benefits of accuracy gain and hinders the adoption of new models. To mitigate regression errors from model upgrade, distillation and ensemble have proven to be viable solutions without significant compromise in performance. Despite the progress, these approaches attained an incremental reduction in regression which is still far from achieving backward-compatible model upgrade. In this work, we propose a novel method, Gated Fusion, that promotes backward compatibility via learning to mix predictions between old and new models. Empirical results on two distinct model upgrade scenarios show that our method reduces the number of regression errors by 62% on average, outperforming the strongest baseline by an average of 25%.

cs.CL↗

arXiv2023

A room-temperature moiré interlayer exciton laser

Moiré superlattices in van der Waals heterostructures offer highly tunable quantum systems with emergent electronic and excitonic properties such as superconductivity, topological edge states, and moiré-trapped excitons. Theoretical calculations predicted the existence of the moiré potential at elevated temperatures; however, its impact on the optical properties of interlayer excitons (IXs) at room temperature is lacking, and the benefits of the moiré effects for lasing applications remain unexplored. We report that the moiré potential in a molybdenum disulfide/tungsten diselenide (MoS2/WSe2) heterobilayer system can significantly enhance light emission, elongate the IX lifetime, and modulate the IX emission energy at room temperature. By integrating a moiré superlattice with a silicon topological nanocavity, we achieve ultra-low-threshold lasing at the technologically important telecommunication O-band thanks to the significant moiré modulation. Moreover, the high-quality topological nanocavities facilitate the highest spectral coherence of < 0.1 nm linewidth among all reported two-dimensional material-based laser systems. Our findings not only open a new avenue for studying correlated states at elevated temperatures, but also enable novel architectures for integrated on-chip photonics and optoelectronics.

physics.optics↗

arXiv2023

Hierarchical Disentangled Representation for Invertible Image Denoising and Beyond

Image denoising is a typical ill-posed problem due to complex degradation. Leading methods based on normalizing flows have tried to solve this problem with an invertible transformation instead of a deterministic mapping. However, the implicit bijective mapping is not explored well. Inspired by a latent observation that noise tends to appear in the high-frequency part of the image, we propose a fully invertible denoising method that injects the idea of disentangled learning into a general invertible neural network to split noise from the high-frequency part. More specifically, we decompose the noisy image into clean low-frequency and hybrid high-frequency parts with an invertible transformation and then disentangle case-specific noise and high-frequency components in the latent space. In this way, denoising is made tractable by inversely merging noiseless low and high-frequency parts. Furthermore, we construct a flexible hierarchical disentangling framework, which aims to decompose most of the low-frequency image information while disentangling noise from the high-frequency part in a coarse-to-fine manner. Extensive experiments on real image denoising, JPEG compressed artifact removal, and medical low-dose CT image restoration have demonstrated that the proposed method achieves competing performance on both quantitative metrics and visual quality, with significantly less computational cost.

cs.CV↗

arXiv2023

Optimization and scheduling for a large scale urban transportation system in a fast-changing world

This paper proposes a set of technological solutions to transform existing transport systems into more intelligent, interactive systems by utilizing optimization and control methods that can be implemented in the near future. This will result in improved public services and quality of life for residents. Three application scenes that are closely related to people's daily life are discussed. We first propose a traffic light scheduling strategy using a model predictive control (MPC) method, with the aim of fairly minimizing delays for both pedestrians and vehicles. Then, a combined dispatching-operation system is proposed to increase control flexibility, with a corresponding implementation solution for boarding control. Finally, a possible scheme to combine both public transport and autonomous vehicle systems is proposed to improve existing public transport systems.

eess.SY↗

arXiv2023

Backward Compatibility During Data Updates by Weight Interpolation

Backward compatibility of model predictions is a desired property when updating a machine learning driven application. It allows to seamlessly improve the underlying model without introducing regression bugs. In classification tasks these bugs occur in the form of negative flips. This means an instance that was correctly classified by the old model is now classified incorrectly by the updated model. This has direct negative impact on the user experience of such systems e.g. a frequently used voice assistant query is suddenly misclassified. A common reason to update the model is when new training data becomes available and needs to be incorporated. Simply retraining the model with the updated data introduces the unwanted negative flips. We study the problem of regression during data updates and propose Backward Compatible Weight Interpolation (BCWI). This method interpolates between the weights of the old and new model and we show in extensive experiments that it reduces negative flips without sacrificing the improved accuracy of the new model. BCWI is straight forward to implement and does not increase inference cost. We also explore the use of importance weighting during interpolation and averaging the weights of multiple new models in order to further reduce negative flips.

cs.LG↗

arXiv2023

On the stable Auslander-Reiten components of certain monomorphism categories

Let $Λ$ be an Artin algebra and let $\rm{Gprj}\mbox{-}Λ$ denote the class of all finitely generated Gorenstein projective $Λ$-modules. In this paper, we study the components of the stable Auslander-Reiten quiver of a certain subcategory of the monomorphism category $\mathcal{S}({\rm Gprj}\mbox{-}Λ)$ containing boundary vertices. We describe the shape of such components. It is shown that certain components are linked to the orbits of an auto-equivalence on the stable category $\underline{\rm{Gprj}}\mbox{-}Λ$. In particular, for the finite components, we show that under certain mild conditions their cardinalities are divisible by $3$. We see that this three-periodicity phenomenon reoccurs several times in the paper.

math.RT↗

arXiv2023

Mottness in two-dimensional van der Waals Nb$_3$X$_8$ monolayers (X=Cl, Br, and I)

We investigate strong electron-electron correlation effects on 2-dimensional van der Waals materials Nb$_3$X$_8$ (X=Cl, Br, I). We find that the monolayers Nb$_3$X$_8$ are ideal systems close to the strong correlation limit. They can be described by a half-filled single band Hubbard model in which the ratio between the Hubbard, U, and the bandwidth, W, U/W $\approx$ 5 $\sim$ 10. Both Mott and magnetic transitions of the material are calculated by the slave boson mean field theory. Doping the Mott state, a $d_{x^2-y^2}+id_{xy}$ superconducting pairing instability is found. We also construct a tunable bilayer Hubbard system for two sliding Nb$_3$X$_8$ layers. The bilayer system displays a crossover between the band insulator and Mott insulator.

cond-mat.str-el↗

arXiv2023

Resilient Containment Control of Heterogeneous Multi-Agent Systems Against Unbounded Sensor and Actuator Attacks

Accurate local state measurement is important to ensure the reliable operation of distributed multi-agent systems (MAS). Existing fault-tolerant control strategies generally assume the sensor faults to be bounded and uncorrelated. In this paper, we study the ramifications of allowing the sensor attack injections to be unbounded and correlated. These malicious sensor attacks may bypass the conventional attack-detection methods and compromise the cooperative performance and even stability of the distributed networked MAS. Moreover, the attackers may gain access to the actuation computing channels and manipulate the control input commands. To this end, we consider the resilient containment control problem of general linear heterogeneous MAS in the face of correlated and unbounded sensor attacks, as well as general unbounded actuator attacks. We propose an attack-resilient control framework to guarantee the uniform ultimate boundedness of the closed-loop dynamical systems and preserve the bounded containment performance. Compared with existing literature addressing bounded faults and/or disturbances that are unintentionally caused in the sensor and actuator channels, the proposed control protocols are resilient against unknown unbounded attack signals simultaneously injected into sensor and actuator channels, and hence are more practical in the real-world security applications. A numerical example illustrates the efficacy of the proposed result, by highlighting the resilience improvement over the conventional cooperative control method.

eess.SY↗

arXiv2023

A Survey on Automated Driving System Testing: Landscapes and Trends

Automated Driving Systems (ADS) have made great achievements in recent years thanks to the efforts from both academia and industry. A typical ADS is composed of multiple modules, including sensing, perception, planning, and control, which brings together the latest advances in different domains. Despite these achievements, safety assurance of ADS is of great significance, since unsafe behavior of ADS can bring catastrophic consequences. Testing has been recognized as an important system validation approach that aims to expose unsafe system behavior; however, in the context of ADS, it is extremely challenging to devise effective testing techniques, due to the high complexity and multidisciplinarity of the systems. There has been great much literature that focuses on the testing of ADS, and a number of surveys have also emerged to summarize the technical advances. Most of the surveys focus on the system-level testing performed within software simulators, and they thereby ignore the distinct features of different modules. In this paper, we provide a comprehensive survey on the existing ADS testing literature, which takes into account both module-level and system-level testing. Specifically, we make the following contributions: (1) we survey the module-level testing techniques for ADS and highlight the technical differences affected by the features of different modules; (2) we also survey the system-level testing techniques, with focuses on the empirical studies that summarize the issues occurring in system development or deployment, the problems due to the collaborations between different modules, and the gap between ADS testing in simulators and the real world; (3) we identify the challenges and opportunities in ADS testing, which pave the path to the future research in this field.

cs.SE↗

arXiv2022

Dialog2API: Task-Oriented Dialogue with API Description and Example Programs

Functionality and dialogue experience are two important factors of task-oriented dialogue systems. Conventional approaches with closed schema (e.g., conversational semantic parsing) often fail as both the functionality and dialogue experience are strongly constrained by the underlying schema. We introduce a new paradigm for task-oriented dialogue - Dialog2API - to greatly expand the functionality and provide seamless dialogue experience. The conversational model interacts with the environment by generating and executing programs triggering a set of pre-defined APIs. The model also manages the dialogue policy and interact with the user through generating appropriate natural language responses. By allowing generating free-form programs, Dialog2API supports composite goals by combining different APIs, whereas unrestricted program revision provides natural and robust dialogue experience. To facilitate Dialog2API, the core model is provided with API documents, an execution environment and optionally some example dialogues annotated with programs. We propose an approach tailored for the Dialog2API, where the dialogue states are represented by a stack of programs, with most recently mentioned program on the top of the stack. Dialog2API can work with many application scenarios such as software automation and customer service. In this paper, we construct a dataset for AWS S3 APIs and present evaluation results of in-context learning baselines.

cs.CL↗

arXiv2022

Social Phases in Human Movement

Recent empirical studies found different thermodynamic phases for collective motion in animals. However, such a thermodynamic description for human movement remains unclear, mainly due to the limited resolution of existing tracking technologies. In this Letter, we used a new ultra-wideband radio frequency identification technology to collect high-resolution spatial-temporal data for classroom movements. We measured the effective temperatures for the underlying systems, and found two social phases, gas and liquid-vapor coexistence, associated with different temperatures. We also proposed a simple statistical physics model that can reproduce different empirically observed phases.

physics.soc-ph↗

arXiv2022

Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems

Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data. Previous studies augmented PLMs with symbolic knowledge for different downstream NLP tasks. However, knowledge bases (KBs) utilized in these studies are usually large-scale and static, in contrast to small, domain-specific, and modifiable knowledge bases that are prominent in real-world task-oriented dialogue (TOD) systems. In this paper, we showcase the advantages of injecting domain-specific knowledge prior to fine-tuning on TOD tasks. To this end, we utilize light-weight adapters that can be easily integrated with PLMs and serve as a repository for facts learned from different KBs. To measure the efficacy of proposed knowledge injection methods, we introduce Knowledge Probing using Response Selection (KPRS) -- a probe designed specifically for TOD models. Experiments on KPRS and the response generation task show improvements of knowledge injection with adapters over strong baselines.

cs.CL↗

arXiv2022

Robust Split Federated Learning for U-shaped Medical Image Networks

U-shaped networks are widely used in various medical image tasks, such as segmentation, restoration and reconstruction, but most of them usually rely on centralized learning and thus ignore privacy issues. To address the privacy concerns, federated learning (FL) and split learning (SL) have attracted increasing attention. However, it is hard for both FL and SL to balance the local computational cost, model privacy and parallel training simultaneously. To achieve this goal, in this paper, we propose Robust Split Federated Learning (RoS-FL) for U-shaped medical image networks, which is a novel hybrid learning paradigm of FL and SL. Previous works cannot preserve the data privacy, including the input, model parameters, label and output simultaneously. To effectively deal with all of them, we design a novel splitting method for U-shaped medical image networks, which splits the network into three parts hosted by different parties. Besides, the distributed learning methods usually suffer from a drift between local and global models caused by data heterogeneity. Based on this consideration, we propose a dynamic weight correction strategy (\textbf{DWCS}) to stabilize the training process and avoid model drift. Specifically, a weight correction loss is designed to quantify the drift between the models from two adjacent communication rounds. By minimizing this loss, a correction model is obtained. Then we treat the weighted sum of correction model and final round models as the result. The effectiveness of the proposed RoS-FL is supported by extensive experimental results on different tasks. Related codes will be released at https://github.com/Zi-YuanYang/RoS-FL.

eess.IV↗

arXiv2022

Boosting Point Clouds Rendering via Radiance Mapping

Recent years we have witnessed rapid development in NeRF-based image rendering due to its high quality. However, point clouds rendering is somehow less explored. Compared to NeRF-based rendering which suffers from dense spatial sampling, point clouds rendering is naturally less computation intensive, which enables its deployment in mobile computing device. In this work, we focus on boosting the image quality of point clouds rendering with a compact model design. We first analyze the adaption of the volume rendering formulation on point clouds. Based on the analysis, we simplify the NeRF representation to a spatial mapping function which only requires single evaluation per pixel. Further, motivated by ray marching, we rectify the the noisy raw point clouds to the estimated intersection between rays and surfaces as queried coordinates, which could avoid \textit{spatial frequency collapse} and neighbor point disturbance. Composed of rasterization, spatial mapping and the refinement stages, our method achieves the state-of-the-art performance on point clouds rendering, outperforming prior works by notable margins, with a smaller model size. We obtain a PSNR of 31.74 on NeRF-Synthetic, 25.88 on ScanNet and 30.81 on DTU. Code and data are publicly available at https://github.com/seanywang0408/RadianceMapping.

cs.CV↗

arXiv2022

AutoPINN: When AutoML Meets Physics-Informed Neural Networks

Physics-Informed Neural Networks (PINNs) have recently been proposed to solve scientific and engineering problems, where physical laws are introduced into neural networks as prior knowledge. With the embedded physical laws, PINNs enable the estimation of critical parameters, which are unobservable via physical tools, through observable variables. For example, Power Electronic Converters (PECs) are essential building blocks for the green energy transition. PINNs have been applied to estimate the capacitance, which is unobservable during PEC operations, using current and voltage, which can be observed easily during operations. The estimated capacitance facilitates self-diagnostics of PECs. Existing PINNs are often manually designed, which is time-consuming and may lead to suboptimal performance due to a large number of design choices for neural network architectures and hyperparameters. In addition, PINNs are often deployed on different physical devices, e.g., PECs, with limited and varying resources. Therefore, it requires designing different PINN models under different resource constraints, making it an even more challenging task for manual design. To contend with the challenges, we propose Automated Physics-Informed Neural Networks (AutoPINN), a framework that enables the automated design of PINNs by combining AutoML and PINNs. Specifically, we first tailor a search space that allows finding high-accuracy PINNs for PEC internal parameter estimation. We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints. We experimentally demonstrate that AutoPINN is able to find more accurate PINN models than human-designed, state-of-the-art PINN models using fewer resources.

cs.LG↗

arXiv2022

HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation

Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centralized global model aggregation. FL suffers from model inaccuracy and slow convergence due to the model heterogeneity of the AIoT devices involved. Although various existing methods try to solve the bottleneck of the model heterogeneity problem, most of them improve the accuracy of heterogeneous models in a coarse-grained manner, which makes it still a great challenge to deploy large-scale AIoT devices. To alleviate the negative impact of this problem and take full advantage of the diversity of each heterogeneous model, we propose an efficient framework named HierarchyFL, which uses a small amount of public data for efficient and scalable knowledge across a variety of differently structured models. By using self-distillation and our proposed ensemble library, each hierarchical model can intelligently learn from each other on cloud servers. Experimental results on various well-known datasets show that HierarchyFL can not only maximize the knowledge sharing among various heterogeneous models in large-scale AIoT systems, but also greatly improve the model performance of each involved heterogeneous AIoT device.

cs.LG↗