arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 865 records · Page 48Linked to original sources

arXiv2021

3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions

The lip is a dominant dynamic facial unit when a person is speaking. Detecting lip events is beneficial to speech analysis and support for the hearing impaired. This paper proposes a 3D lip event detection pipeline that automatically determines the lip events from a 3D speaking lip sequence. We define a motion divergence measure using 3D lip landmarks to quantify the interframe dynamics of a 3D speaking lip. Then, we cast the interframe motion detection in a multi-temporal-resolution framework that allows the detection to be applicable to different speaking speeds. The experiments on the S3DFM Dataset investigate the overall 3D lip dynamics based on the proposed motion divergence. The proposed 3D pipeline is able to detect opening and closing lip events across 100 sequences, achieving a state-of-the-art performance.

cs.CV↗

arXiv2021

Searching for Superconductivity in High Entropy Oxide Ruddlesden-Popper Cuprate Films

In this work, the high entropy oxide A2CuO4 Ruddlesden-Popper (La0.2Pr0.2Nd0.2Sm0.2Eu0.2)2CuO4 is explored by charge doping with Ce+4 and Sr+2 at concentrations known to induce superconductivity in the simple parent compounds, Nd2CuO4 and La2CuO4. Electron doped (La0.185Pr0.185Nd0.185Sm0.185Eu0.185Ce0.075)2CuO4 and hole doped (La0.18Pr0.18Nd0.18Sm0.18Eu0.18Sr0.1)2CuO4 are synthesized and shown to be single crystal, epitaxially strained, and highly uniform. Transport measurements demonstrate that all as-grown films are insulating regardless of doping. Annealing studies show that resistivity can be tuned by modifying oxygen stoichiometry and inducing metallicity but without superconductivity. These results in turn are connected to extended x-ray absorption fine structure (EXAFS) results indicating that the lack of superconductivity in the high entropy cuprates likely originates from a large distortion within the Cu-O plane (σ2>0.015 Å2) due to A-site cation size variance, which drives localization of charge carriers. These findings describe new opportunities for controlling charge- and orbital-mediated functional responses in Ruddlesden-Popper crystal structures, driven by balancing of cation size and charge variances that may be exploited for functionally important behaviors such as superconductivity, antiferromagnetism, and metal-insulator transitions, while opening less understood phase spaces hosting doped Mott insulators, strange metals, quantum criticality, pseudogaps, and ordered charge density waves.

cond-mat.supr-con↗

arXiv2021

A lightweight blockchain-based access control scheme for integrated edge computing in the internet of things

In view of the security issues of the Internet of Things (IoT), considered better combining edge computing and blockchain with the IoT, integrating attribute-based encryption (ABE) and attribute-based access control (ABAC) models with attributes as the entry point, an attribute-based encryption and access control scheme (ABE-ACS) has been proposed. Facing Edge-Iot, which is a heterogeneous network composed of most resource-limited IoT devices and some nodes with higher computing power. For the problems of high resource consumption and difficult deployment of existing blockchain platforms, we design a lightweight blockchain (LBC) with improvement of the proof-of-work consensus. For the access control policies, the threshold tree and LSSS are used for conversion and assignment, stored in the blockchain to protect the privacy of the policy. For device and data, six smart contracts are designed to realize the ABAC and penalty mechanism, with which ABE is outsourced to edge nodes for privacy and integrity. Thus, our scheme realizing Edge-Iot privacy protection, data and device controlled access. The security analysis shows that the proposed scheme is secure and the experimental results show that our LBC has higher throughput and lower resources consumption, the cost of encryption and decryption of our scheme is desirable.

cs.CR↗

arXiv2021

Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems

Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily. To capture the most recent trends effectively, it is common to update the model incrementally using only the newly arrived data. However, this may impede the model's ability to retain long-term information due to the potential overfitting and forgetting issues. To address this problem, we propose a novel Adaptive Sequential Model Generation (ASMG) framework, which generates a better serving model from a sequence of historical models via a meta generator. For the design of the meta generator, we propose to employ Gated Recurrent Units (GRUs) to leverage its ability to capture the long-term dependencies. We further introduce some novel strategies to apply together with the GRU meta generator, which not only improve its computational efficiency but also enable more accurate sequential modeling. By instantiating the model-agnostic framework on a general deep learning-based RS model, we demonstrate that our method achieves state-of-the-art performance on three public datasets and one industrial dataset.

cs.IR↗

arXiv2021

Parameterized Knowledge Transfer for Personalized Federated Learning

In recent years, personalized federated learning (pFL) has attracted increasing attention for its potential in dealing with statistical heterogeneity among clients. However, the state-of-the-art pFL methods rely on model parameters aggregation at the server side, which require all models to have the same structure and size, and thus limits the application for more heterogeneous scenarios. To deal with such model constraints, we exploit the potentials of heterogeneous model settings and propose a novel training framework to employ personalized models for different clients. Specifically, we formulate the aggregation procedure in original pFL into a personalized group knowledge transfer training algorithm, namely, KT-pFL, which enables each client to maintain a personalized soft prediction at the server side to guide the others' local training. KT-pFL updates the personalized soft prediction of each client by a linear combination of all local soft predictions using a knowledge coefficient matrix, which can adaptively reinforce the collaboration among clients who own similar data distribution. Furthermore, to quantify the contributions of each client to others' personalized training, the knowledge coefficient matrix is parameterized so that it can be trained simultaneously with the models. The knowledge coefficient matrix and the model parameters are alternatively updated in each round following the gradient descent way. Extensive experiments on various datasets (EMNIST, Fashion\_MNIST, CIFAR-10) are conducted under different settings (heterogeneous models and data distributions). It is demonstrated that the proposed framework is the first federated learning paradigm that realizes personalized model training via parameterized group knowledge transfer while achieving significant performance gain comparing with state-of-the-art algorithms.

cs.LG↗

arXiv2021

Learning Large Neighborhood Search Policy for Integer Programming

We propose a deep reinforcement learning (RL) method to learn large neighborhood search (LNS) policy for integer programming (IP). The RL policy is trained as the destroy operator to select a subset of variables at each step, which is reoptimized by an IP solver as the repair operator. However, the combinatorial number of variable subsets prevents direct application of typical RL algorithms. To tackle this challenge, we represent all subsets by factorizing them into binary decisions on each variable. We then design a neural network to learn policies for each variable in parallel, trained by a customized actor-critic algorithm. We evaluate the proposed method on four representative IP problems. Results show that it can find better solutions than SCIP in much less time, and significantly outperform other LNS baselines with the same runtime. Moreover, these advantages notably persist when the policies generalize to larger problems. Further experiments with Gurobi also reveal that our method can outperform this state-of-the-art commercial solver within the same time limit.

cs.AI↗

arXiv2021

M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining

Recent expeditious developments in deep learning algorithms, distributed training, and even hardware design for large models have enabled training extreme-scale models, say GPT-3 and Switch Transformer possessing hundreds of billions or even trillions of parameters. However, under limited resources, extreme-scale model training that requires enormous amounts of computes and memory footprint suffers from frustratingly low efficiency in model convergence. In this paper, we propose a simple training strategy called "Pseudo-to-Real" for high-memory-footprint-required large models. Pseudo-to-Real is compatible with large models with architecture of sequential layers. We demonstrate a practice of pretraining unprecedented 10-trillion-parameter model, an order of magnitude larger than the state-of-the-art, on solely 512 GPUs within 10 days. Besides demonstrating the application of Pseudo-to-Real, we also provide a technique, Granular CPU offloading, to manage CPU memory for training large model and maintain high GPU utilities. Fast training of extreme-scale models on a decent amount of resources can bring much smaller carbon footprint and contribute to greener AI.

cs.LG↗

arXiv2021

Self-regulated growth of candidate topological superconducting parkerite by molecular beam epitaxy

Ternary chalcogenides such as the parkerites and shandites are a broad class of materials exhibiting rich diversity of transport and magnetic behavior as well as an array of topological phases including Weyl and Dirac nodes. However, they remain largely unexplored as high-quality epitaxial thin films. Here, we report the self-regulated growth of thin films of the strong spin-orbit coupled superconductor Pd3Bi2Se2 on SrTiO3 by molecular beam epitaxy. Films are found to grow in a self-regulated fashion, where, in excess Se, the temperature and relative flux ratio of Pd to Bi controls the formation of Pd3Bi2Se2 due to the combined volatility of Bi, Se, and Bi-Se bonded phases. The resulting films are shown to be of high structural quality, the stoichiometry is independent of the Pd:Bi and Se flux ratio and exhibit a superconducting transition temperature of 800 mK and critical field of 17.7 +/- 0.5 mT, as probed by transport as well as magnetometry. Understanding and navigating the growth of the chemically and structurally diverse classes of ternary chalcogenides opens a vast space for discovering new phenomena as well as enabling new applications.

cond-mat.mtrl-sci↗

arXiv2021

SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing

The operation and management of intelligent transportation systems (ITS), such as traffic monitoring, relies on real-time data aggregation of vehicular traffic information, including vehicular types (e.g., cars, trucks, and buses), in the critical roads and highways. While traditional approaches based on vehicular-embedded GPS sensors or camera networks would either invade drivers' privacy or require high deployment cost, this paper introduces a low-cost method, namely SenseMag, to recognize the vehicular type using a pair of non-invasive magnetic sensors deployed on the straight road section. SenseMag filters out noises and segments received magnetic signals by the exact time points that the vehicle arrives or departs from every sensor node. Further, SenseMag adopts a hierarchical recognition model to first estimate the speed/velocity, then identify the length of vehicle using the predicted speed, sampling cycles, and the distance between the sensor nodes. With the vehicle length identified and the temporal/spectral features extracted from the magnetic signals, SenseMag classify the types of vehicles accordingly. Some semi-automated learning techniques have been adopted for the design of filters, features, and the choice of hyper-parameters. Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i.e., 7 types by SenseMag versus 4 types by the existing work in comparisons). To be specific, our field experiment results validate that SenseMag is with at least $90\%$ vehicle type classification accuracy and less than 5\% vehicle length classification error.

cs.LG↗

arXiv2021

Design and realization of Ohmic and Schottky interfaces for oxide electronics

Understanding band alignment and charge transfer at complex oxide interfaces is critical to tailoring and utilizing their diverse functionality. Towards this goal, we design and experimentally validate both Ohmic- and Schottky-like charge transfers at oxide/oxide semiconductor/metal interfaces. We utilize a method for predicting band alignment and charge transfer in ABO3 perovskites, where previously established rules for simple semiconductors fail. The prototypical systems chosen are the rare class of oxide metals, SrBO3 with B=V-Ta, when interfaced with the multifaceted semiconducting oxide, SrTiO3. For B=Nb and Ta, we confirm that a large accumulation of charge occurs in SrTiO3 due to higher energy Nb and Ta d-states relative to Ti; this gives rise to a high mobility metallic interface, which is an ideal epitaxial oxide/oxide Ohmic contact. On the other hand, for B=V, there is no charge transfer into the SrTiO3 interface, which serves as a highly conductive epitaxial gate metal. Going beyond these specific cases, this work opens the door to integrating the vast phenomena of ABO3 perovskites into a wide range of practical devices.

cond-mat.mtrl-sci↗

arXiv2021

Fundamental Wireless Performance of a Building

Over 80% of wireless traffic already takes place in buildings. Like water, gas, and electricity, wireless communication is becoming one of the most fundamental utilities of a building. It is well known that building structures have a significant impact on in-building wireless networks. If we seek to achieve the optimal network performance indoors, the buildings should be designed with the objective of maximizing wireless performance. So far, wireless performance has not yet been considered when designing a building. In this paper, we introduce a novel and interdisciplinary concept of building wireless performance (BWP) to a wide audience in both wireless communications and building design, emphasizing its broad impacts on wireless network development and deployment, and on building layout/material design. We first give an overview of the BWP evaluation framework proposed in our state-of-the-art works and explain their interconnections. Then, we outline the potential research directions in this exciting research area to encourage further interdisciplinary research.

cs.NI↗

arXiv2021

Cross-Vendor CT Image Data Harmonization Using CVH-CT

While remarkable advances have been made in Computed Tomography (CT), most of the existing efforts focus on imaging enhancement while reducing radiation dose. How to harmonize CT image data captured using different scanners is vital in cross-center large-scale radiomics studies but remains the boundary to explore. Furthermore, the lack of paired training image problem makes it computationally challenging to adopt existing deep learning models. %developed for CT image standardization. %this problem more challenging. We propose a novel deep learning approach called CVH-CT for harmonizing CT images captured using scanners from different vendors. The generator of CVH-CT uses a self-attention mechanism to learn the scanner-related information. We also propose a VGG feature-based domain loss to effectively extract texture properties from unpaired image data to learn the scanner-based texture distributions. The experimental results show that CVH-CT is clearly better than the baselines because of the use of the proposed domain loss, and CVH-CT can effectively reduce the scanner-related variability in terms of radiomic features.

eess.IV↗

arXiv2021

NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem

We present NeuroLKH, a novel algorithm that combines deep learning with the strong traditional heuristic Lin-Kernighan-Helsgaun (LKH) for solving Traveling Salesman Problem. Specifically, we train a Sparse Graph Network (SGN) with supervised learning for edge scores and unsupervised learning for node penalties, both of which are critical for improving the performance of LKH. Based on the output of SGN, NeuroLKH creates the edge candidate set and transforms edge distances to guide the searching process of LKH. Extensive experiments firmly demonstrate that, by training one model on a wide range of problem sizes, NeuroLKH significantly outperforms LKH and generalizes well to much larger sizes. Also, we show that NeuroLKH can be applied to other routing problems such as Capacitated Vehicle Routing Problem (CVRP), Pickup and Delivery Problem (PDP), and CVRP with Time Windows (CVRPTW).

cs.AI↗

arXiv2021

Critical behaviors of jamming in cyclically sheared frictional hard granular particles

In stark contrast to the jamming of frictionless hard-sphere (hard-disk if in two dimensions) packings, the critical jamming of frictional packings is much more elusive and still under intense debate. Here we show that frictional hard-disk packings self-organize near a critical jamming state when subjected to quasi-static steady-state cyclic shear, displaying scale-free fluctuations in particle velocity fields as characterized by the power spectra $E(k)\propto k^{-α}$ for both longitudinal and transverse modes in wavevector space, with $α\approx2.0\pm0.15$, and the nearly flat spectra $E(ω)\propto const.$ in angular frequency domain. Our findings agree quantitatively with the predictions of the Langevin-type effective medium theory of S. Henkes and coworkers with two diverging length scales associated respectively with the longitudinal and transverse modes, showing a hallmark of critical behaviors of jamming. Moreover, our findings are consistent with the conceptual framework of general isostaticity but with a key difference that the system self-organizes to a critical jamming state through a strong coupling of mechanical structure and dynamics. Our findings are important in providing microscopic mechanism in understanding the nonlocal rheologies and guide principles in developing constitutive relations of real granular materials.

cond-mat.soft↗

arXiv2021

Fast Laser Cooling Using Optimal Quantum Control

Cooling down a trapped ion into its motional ground state is a central step for trapped ions based quantum information processing. State of the art cooling schemes often work under a set of optimal cooling conditions derived analytically using a perturbative approach, in which the sideband coupling is assumed to be the weakest of all the relevant transitions. As a result the cooling rate is severely limited. Here we propose to use quantum control technique powered with automatic differentiation to speed up the classical cooling schemes. We demonstrate the efficacy of our approach by applying it to find the optimal cooling conditions for classical sideband cooling and electromagnetically induced transparency cooling schemes, which are in general beyond the weak sideband coupling regime. Based on those numerically found optimal cooling conditions, we show that faster cooling can be achieved while at the same time a low average phonon occupation can be retained.

quant-ph↗

arXiv2021

Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning

Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and delivery problem (PDP), which is a representative variant of VRP. To address this challenging issue, we leverage a novel neural network integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes. In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the nodes while taking into account the precedence constraint, i.e., the pickup node must precede the pairing delivery node. Further integrated with a masking scheme, the learnt policy is expected to find higher-quality solutions for solving PDP. Extensive experimental results show that our method outperforms the state-of-the-art heuristic and deep learning model, respectively, and generalizes well to different distributions and problem sizes.

cs.LG↗

arXiv2021

ACDC: Online Unsupervised Cross-Domain Adaptation

We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together. Unique characteristics and challenges such as covariate shift, asynchronous concept drifts, and contrasting data throughput arises. We propose ACDC, an adversarial unsupervised domain adaptation framework that handles multiple data streams with a complete self-evolving neural network structure that reacts to these defiances. ACDC encapsulates three modules into a single model: A denoising autoencoder that extracts features, an adversarial module that performs domain conversion, and an estimator that learns the source stream and predicts the target stream. ACDC is a flexible and expandable framework with little hyper-parameter tunability. Our experimental results under the prequential test-then-train protocol indicate an improvement in target accuracy over the baseline methods, achieving more than a 10\% increase in some cases.

cs.LG↗

arXiv2021

Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark

Recognizing the emotional state of people is a basic but challenging task in video understanding. In this paper, we propose a new task in this field, named Pairwise Emotional Relationship Recognition (PERR). This task aims to recognize the emotional relationship between the two interactive characters in a given video clip. It is different from the traditional emotion and social relation recognition task. Varieties of information, consisting of character appearance, behaviors, facial emotions, dialogues, background music as well as subtitles contribute differently to the final results, which makes the task more challenging but meaningful in developing more advanced multi-modal models. To facilitate the task, we develop a new dataset called Emotional RelAtionship of inTeractiOn (ERATO) based on dramas and movies. ERATO is a large-scale multi-modal dataset for PERR task, which has 31,182 video clips, lasting about 203 video hours. Different from the existing datasets, ERATO contains interaction-centric videos with multi-shots, varied video length, and multiple modalities including visual, audio and text. As a minor contribution, we propose a baseline model composed of Synchronous Modal-Temporal Attention (SMTA) unit to fuse the multi-modal information for the PERR task. In contrast to other prevailing attention mechanisms, our proposed SMTA can steadily improve the performance by about 1\%. We expect the ERATO as well as our proposed SMTA to open up a new way for PERR task in video understanding and further improve the research of multi-modal fusion methodology.

cs.CV↗