Searcharxiv⌕ Search

arXiv subjects

Chao Yang

Publications and source records attributed to Chao Yang.

At least 271 records · Page 15Linked to original sources

GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce

Our goal is to build general representation (embedding) for each user and each product item across Alibaba's businesses, including Taobao and Tmall which are among the world's biggest e-commerce websites. The representation of users and items has been playing a critical role in various downstream applications, including recommendation system, search, marketing, demand forecasting and so on. Inspired from the BERT model in natural language processing (NLP) domain, we propose a GUIM (General User Item embedding with Mixture of representation) model to achieve the goal with massive, structured, multi-modal data including the interactions among hundreds of millions of users and items. We utilize mixture of representation (MoR) as a novel representation form to model the diverse interests of each user. In addition, we use the InfoNCE from contrastive learning to avoid intractable computational costs due to the numerous size of item (token) vocabulary. Finally, we propose a set of representative downstream tasks to serve as a standard benchmark to evaluate the quality of the learned user and/or item embeddings, analogous to the GLUE benchmark in NLP domain. Our experimental results in these downstream tasks clearly show the comparative value of embeddings learned from our GUIM model.

cs.AI↗

PFNN-2: A Domain Decomposed Penalty-Free Neural Network Method for Solving Partial Differential Equations

A new penalty-free neural network method, PFNN-2, is presented for solving partial differential equations, which is a subsequent improvement of our previously proposed PFNN method [1]. PFNN-2 inherits all advantages of PFNN in handling the smoothness constraints and essential boundary conditions of self-adjoint problems with complex geometries, and extends the application to a broader range of non-self-adjoint time-dependent differential equations. In addition, PFNN-2 introduces an overlapping domain decomposition strategy to substantially improve the training efficiency without sacrificing accuracy. Experiments results on a series of partial differential equations are reported, which demonstrate that PFNN-2 can outperform state-of-the-art neural network methods in various aspects such as numerical accuracy, convergence speed, and parallel scalability.

math.NA↗

$2^{1296}$ Exponentially Complex Quantum Many-Body Simulation via Scalable Deep Learning Method

For decades, people are developing efficient numerical methods for solving the challenging quantum many-body problem, whose Hilbert space grows exponentially with the size of the problem. However, this journey is far from over, as previous methods all have serious limitations. The recently developed deep learning methods provide a very promising new route to solve the long-standing quantum many-body problems. We report that a deep learning based simulation protocol can achieve the solution with state-of-the-art precision in the Hilbert space as large as $2^{1296}$ for spin system and $3^{144}$ for fermion system , using a HPC-AI hybrid framework on the new Sunway supercomputer. With highly scalability up to 40 million heterogeneous cores, our applications have measured 94% weak scaling efficiency and 72% strong scaling efficiency. The accomplishment of this work opens the door to simulate spin models and Fermion models on unprecedented lattice size with extreme high precision.

quant-ph↗

Using dynamic mode decomposition to predict the dynamics of a two-time non-equilibrium Green's function

Computing the numerical solution of the Kadanoff-Baym equations, a set of nonlinear integral differential equations satisfied by two-time Green's functions derived from many-body perturbation theory for a quantum many-body system away from equilibrium, is a challenging task. Recently, we have successfully applied dynamic mode decomposition (DMD) to construct a data driven reduced order model that can be used to extrapolate the time-diagonal of a two-time Green's function from numerical solution of the KBE within a small time window. In this paper, we extend the previous work and use DMD to predict off-diagonal elements of the two-time Green's function. We partition the two-time Green's function into a number of one-time functions along the diagonal and subdiagonls of the two-time window as well as in horizontal and vertical directions. We use DMD to construct separate reduced order models to predict the dynamics of these one-time functions in a two-step procedure. We extrapolate along diagonal and several subdiagonals within a subdiagonal band of a two-time window in the first step. In the second step, we use DMD to extrapolate the Green's function outside of the sub-diagonal band. We demonstrate the efficiency and accuracy of this approach by applying it to a two-band Hubbard model problem.

cond-mat.str-el↗

Randomized Algorithms for Scientific Computing (RASC)

Randomized algorithms have propelled advances in artificial intelligence and represent a foundational research area in advancing AI for Science. Future advancements in DOE Office of Science priority areas such as climate science, astrophysics, fusion, advanced materials, combustion, and quantum computing all require randomized algorithms for surmounting challenges of complexity, robustness, and scalability. This report summarizes the outcomes of that workshop, "Randomized Algorithms for Scientific Computing (RASC)," held virtually across four days in December 2020 and January 2021.

cs.AI↗

A Robust Multimodal Remote Sensing Image Registration Method and System Using Steerable Filters with First- and Second-order Gradients

Co-registration of multimodal remote sensing images is still an ongoing challenge because of nonlinear radiometric differences (NRD) and significant geometric distortions (e.g., scale and rotation changes) between these images. In this paper, a robust matching method based on the Steerable filters is proposed consisting of two critical steps. First, to address severe NRD, a novel structural descriptor named the Steerable Filters of first- and second-Order Channels (SFOC) is constructed, which combines the first- and second-order gradient information by using the steerable filters with a multi-scale strategy to depict more discriminative structure features of images. Then, a fast similarity measure is established called Fast Normalized Cross-Correlation (Fast-NCCSFOC), which employs the Fast Fourier Transform technique and the integral image to improve the matching efficiency. Furthermore, to achieve reliable registration performance, a coarse-to-fine multimodal registration system is designed consisting of two pivotal modules. The local coarse registration is first conducted by involving both detection of interest points (IPs) and local geometric correction, which effectively utilizes the prior georeferencing information of RS images to address global geometric distortions. In the fine registration stage, the proposed SFOC is used to resist significant NRD, and to detect control points between multimodal images by a template matching scheme. The performance of the proposed matching method has been evaluated with many different kinds of multimodal RS images. The results show its superior matching performance compared with the state-of-the-art methods. Moreover, the designed registration system also outperforms the popular commercial software in both registration accuracy and computational efficiency. Our system is available at https://github.com/yeyuanxin110.

cs.CV↗

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of speaking styles, scenarios, domains, topics, and noisy conditions. An optical character recognition (OCR) based method is introduced to generate the audio/text segmentation candidates for the YouTube data on its corresponding video captions, while a high-quality ASR transcription system is used to generate audio/text pair candidates for the Podcast data. Then we propose a novel end-to-end label error detection approach to further validate and filter the candidates. We also provide three manually labelled high-quality test sets along with WenetSpeech for evaluation -- Dev for cross-validation purpose in training, Test_Net, collected from Internet for matched test, and Test\_Meeting, recorded from real meetings for more challenging mismatched test. Baseline systems trained with WenetSpeech are provided for three popular speech recognition toolkits, namely Kaldi, ESPnet, and WeNet, and recognition results on the three test sets are also provided as benchmarks. To the best of our knowledge, WenetSpeech is the current largest open-sourced Mandarin speech corpus with transcriptions, which benefits research on production-level speech recognition.

cs.SD↗

Topological Authentication Technique In Topologically Asymmetric Cryptosystem

Making topological authentication from theory to practical application is an important and challenging task. More and more researchers pay attention on coming quantum computation, privacy data protection, lattices and cryptography. Research show the advantages of topological authentications through graph operations, various matrices, graph colorings and graph labelings are: related with two or more different mathematical areas, be not pictures, there are huge number of colorings and labelings, rooted on modern mathematics, diversity of asymmetric ciphers, simplicity and convenience, easily created, irreversibility, computational security, provable security, and so on. Topological authentications based on various graph homomorphisms, degree-sequence homomorphisms, graph-set homomorphisms. Randomly topological coding and topological authentications are based on Hanzi authentication, randomly adding-edge-removing operation, randomly leaf-adding algorithms, graph random increasing techniques, operation graphic lattice and dynamic networked models and their spanning trees and maximum leaf spanning trees. Realization of topological authentication is an important topic, we study: number-based strings generated from colored graphs, particular graphs (complete graphs, trees, planar graphs), some methods of generating public-keys. some techniques of topologically asymmetric cryptosystem are: W-type matching labelings, dual-type labelings, reciprocal-type labelings, topological homomorphisms, indexed colorings, graphic lattices, degree-sequence lattices, every-zero Cds-matrix groups of degree-sequences, every-zero graphic groups, graphic lattices having coloring closure property, self-similar networked lattices.

cs.CR↗

Sim2Real Object-Centric Keypoint Detection and Description

Keypoint detection and description play a central role in computer vision. Most existing methods are in the form of scene-level prediction, without returning the object classes of different keypoints. In this paper, we propose the object-centric formulation, which, beyond the conventional setting, requires further identifying which object each interest point belongs to. With such fine-grained information, our framework enables more downstream potentials, such as object-level matching and pose estimation in a clustered environment. To get around the difficulty of label collection in the real world, we develop a sim2real contrastive learning mechanism that can generalize the model trained in simulation to real-world applications. The novelties of our training method are three-fold: (i) we integrate the uncertainty into the learning framework to improve feature description of hard cases, e.g., less-textured or symmetric patches; (ii) we decouple the object descriptor into two output branches -- intra-object salience and inter-object distinctness, resulting in a better pixel-wise description; (iii) we enforce cross-view semantic consistency for enhanced robustness in representation learning. Comprehensive experiments on image matching and 6D pose estimation verify the encouraging generalization ability of our method from simulation to reality. Particularly for 6D pose estimation, our method significantly outperforms typical unsupervised/sim2real methods, achieving a closer gap with the fully supervised counterpart. Additional results and videos can be found at https://zhongcl-thu.github.io/rock/

cs.CV↗

An extension on neighbor sum distinguishing total coloring of graphs

Let $f: V(G)\cup E(G)\rightarrow \{1,2,\dots,k\}$ be a non-proper total $k$-coloring of $G$. Define a weight function on total coloring as $$ϕ(x)=f(x)+\sum\limits_{e\ni x}f(e)+\sum\limits_{y\in N(x)}f(y),$$ where $N(x)=\{y\in V(G)|xy\in E(G)\}$. If $ϕ(x)\neq ϕ(y)$ for any edge $xy\in E(G)$, then $f$ is called a neighbor full sum distinguishing total $k$-coloring of $G$. The smallest value $k$ for which $G$ has such a coloring is called the neighbor full sum distinguishing total chromatic number of $G$ and denoted by fgndi$_{\sum}(G)$. The coloring is an extension of neighbor sum distinguishing non-proper total coloring. In this paper we conjecture that fgndi$_{\sum}(G)\leq 3$ for any connected graph $G$ of order at least three. We prove that the conjecture is true for (i) paths and cycles; (ii) 3-regular graphs and (iii) stars, complete graphs, trees, hypercubes, bipartite graphs and complete $r$-partite graphs. In particular, complete graphs can achieve the upper bound for the above conjecture.

math.CO↗

U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition

The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time factor (RTF), and latency. In this paper, we present U2++, an enhanced version of U2 to further improve the accuracy. The core idea of U2++ is to use the forward and the backward information of the labeling sequences at the same time at training to learn richer information, and combine the forward and backward prediction at decoding to give more accurate recognition results. We also proposed a new data augmentation method called SpecSub to help the U2++ model to be more accurate and robust. Our experiments show that, compared with U2, U2++ shows faster convergence at training, better robustness to the decoding method, as well as consistent 5\% - 8\% word error rate reduction gain over U2. On the experiment of AISHELL-1, we achieve a 4.63\% character error rate (CER) with a non-streaming setup and 5.05\% with a streaming setup with 320ms latency by U2++. To the best of our knowledge, 5.05\% is the best-published streaming result on the AISHELL-1 test set.

cs.SD↗

Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. This efficient rescoring process causes very little sentence-level latency. Our experiments on the open 170-hour AISHELL-1 dataset show that, the proposed method can unify the streaming and non-streaming model simply and efficiently. On the AISHELL-1 test set, our unified model achieves 5.60% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. The same model achieves 5.42% CER with 640ms latency in a streaming ASR system.

cs.SD↗

WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. The main motivation of WeNet is to close the gap between the research and the production of E2E speechrecognition models. WeNet provides an efficient way to ship ASR applications in several real-world scenarios, which is the main difference and advantage to other open source E2E speech recognition toolkits. In our toolkit, a new two-pass method is implemented. Our method propose a dynamic chunk-based attention strategy of the the transformer layers to allow arbitrary right context length modifies in hybrid CTC/attention architecture. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. Our experiments on the AISHELL-1 dataset using WeNet show that, our model achieves 5.03\% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. After model quantification, our model perform reasonable RTF and latency.

cs.SD↗

Yaw attitudes for BDS-3 IGSO and MEO satellites: estimation, validation and modeling with inter-satellite link observations

The disclosed satellite metadata as well as previous estimations using Revise Kinematic Precise Point Positioning (RKPPP) approach with L-band data have already demonstrated the continuous yaw steering model used by BDS-3 Medium Earth Orbit (MEO) satellites manufactured by China Academy of Space Technology (CAST) in deep eclipse seasons instead of the orbit normal mode. However, the yaw model has not been validated for MEO satellites manufactured by Shanghai Engineering Center of Microsatellites (SECM), as the horizontal phase center offsets (PCO) approaches zeros, similar for BDS-3 Inclined Geostationary Orbit (IGSO) satellites. In this study, the inter-satellite link (ISL) data were used to estimate the yaw angles of BDS-3 IGSO and MEO satellites with accuracy of around 1.49° to investigate their yaw behaviors, particularly in the deep eclipse seasons. The estimates confirm that the IGSO and MEO satellites from CAST show the similar yaw behaviors, while the SECM MEO satellites do not fully comply with the attitude law published by China Satellite Navigation Office (CSNO). The attitude transition postpones from that predicted by CSNO yaw law, and occurs when the yaw angle is less than 5° and the elevation angle of the Sun above the orbital plane (beta angle) crosses 0°. The transition completes within three minutes with a rate about 0.055°/s. A model is proposed to predict these behaviors, and the ISL residuals return to normal levels, and became more stable in the adjacent of midnight and noon points. Once the yaw models are used.

astro-ph.IM↗

VPVnet: a velocity-pressure-vorticity neural network method for the Stokes' equations under reduced regularity

We present VPVnet, a deep neural network method for the Stokes' equations under reduced regularity. Different with recently proposed deep learning methods [40,51] which are based on the original form of PDEs, VPVnet uses the least square functional of the first-order velocity-pressure-vorticity (VPV) formulation ([30]) as loss functions. As such, only first-order derivative is required in the loss functions, hence the method is applicable to a much larger class of problems, e.g. problems with non-smooth solutions. Despite that several methods have been proposed recently to reduce the regularity requirement by transforming the original problem into a corresponding variational form, while for the Stokes' equations, the choice of approximating spaces for the velocity and the pressure has to satisfy the LBB condition additionally. Here by making use of the VPV formulation, lower regularity requirement is achieved with no need for considering the LBB condition. Convergence and error estimates have been established for the proposed method. It is worth emphasizing that the VPVnet method is divergence-free and pressure-robust, while classical inf-sup stable mixed finite elements for the Stokes' equations are not pressure-robust. Various numerical experiments including 2D and 3D lid-driven cavity test cases are conducted to demonstrate its efficiency and accuracy.

math.NA↗

Parallel finite volume simulation of the spherical shell dynamo with pseudo-vacuum magnetic boundary conditions

In this paper, we study the parallel simulation of the magnetohydrodynamic (MHD) dynamo in a rapidly rotating spherical shell with pseudo-vacuum magnetic boundary conditions. A second-order finite volume scheme based on a collocated quasi-uniform cubed-sphere grid is applied to the spatial discretization of the MHD dynamo equations. To ensure the solenoidal condition of the magnetic field, we adopt a widely-used approach whereby a pseudo-pressure is introduced into the induction equation. The temporal integration is split by a second-order approximate factorization approach, resulting in two linear algebraic systems both solved by a preconditioned Krylov subspace iterative method. A multi-level restricted additive Schwarz preconditioner based on domain decomposition and multigrid method is then designed to improve the efficiency and scalability. Accurate numerical solutions of two benchmark cases are obtained with our code, comparable to the existing local method results. Several large-scale tests performed on the Sunway TaihuLight supercomputer show good strong and weak scalabilities and a noticeable improvement from the multi-level preconditioner with up to 10368 processor cores.

physics.comp-ph↗

Establishing a non-hydrostatic global atmospheric modeling system (iAMAS) at 3-km horizontal resolution with online integrated aerosol feedbacks on the Sunway supercomputer of China

During the era of global warming and highly urbanized development, extreme and high impact weather as well as air pollution incidents influence everyday life and might even cause the incalculable loss of life and property. Although with the vast development of numerical simulation of atmosphere, there still exists substantial forecast biases objectively. To predict extreme weather, severe air pollution, and abrupt climate change accurately, the numerical atmospheric model requires not only to simulate meteorology and atmospheric compositions and their impacts simultaneously involving many sophisticated physical and chemical processes but also at high spatiotemporal resolution. Global atmospheric simulation of meteorology and atmospheric compositions simultaneously at spatial resolutions of a few kilometers remains challenging due to its intensive computational and input/output (I/O) requirement. Through multi-dimension-parallelism structuring, aggressive and finer-grained optimizing, manual vectorizing, and parallelized I/O fragmenting, an integrated Atmospheric Model Across Scales (iAMAS) was established on the new Sunway supercomputer platform to significantly increase the computational efficiency and reduce the I/O cost. The global 3-km atmospheric simulation for meteorology with online integrated aerosol feedbacks with iAMAS was scaled to 39,000,000 processor cores and achieved the speed of 0.82 simulation day per hour (SDPH) with routine I/O, which enables us to perform 5-day global weather forecast at 3-km horizontal resolution with online natural aerosol impacts. The results demonstrate the promising future that the increasing of spatial resolution to a few kilometers with online integrated aerosol impacts may significantly improve the global weather forecast.

physics.ao-ph↗

Control Parameters Considered Harmful: Detecting Range Specification Bugs in Drone Configuration Modules via Learning-Guided Search

In order to support a variety of missions and deal with different flight environments, drone control programs typically provide configurable control parameters. However, such a flexibility introduces vulnerabilities. One such vulnerability, referred to as range specification bugs, has been recently identified. The vulnerability originates from the fact that even though each individual parameter receives a value in the recommended value range, certain combinations of parameter values may affect the drone physical stability. In this paper we develop a novel learning-guided search system to find such combinations, that we refer to as incorrect configurations. Our system applies metaheuristic search algorithms mutating configurations to detect the configuration parameters that have values driving the drone to unstable physical states. To guide the mutations, our system leverages a machine learning predictor as the fitness evaluator. Finally, by utilizing multi-objective optimization, our system returns the feasible ranges based on the mutation search results. Because in our system the mutations are guided by a predictor, evaluating the parameter configurations does not require realistic/simulation executions. Therefore, our system supports a comprehensive and yet efficient detection of incorrect configurations. We have carried out an experimental evaluation of our system. The evaluation results show that the system successfully reports potentially incorrect configurations, of which over 85% lead to actual unstable physical states.

cs.RO↗