arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 865 records · Page 48Linked to original sources

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↗

arXiv2021

Graph Random Neural Network for Semi-Supervised Learning on Graphs

We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, non-robustness, and weak-generalization when labeled nodes are scarce. In this paper, we propose a simple yet effective framework -- GRAPH RANDOM NEURAL NETWORKS (GRAND) -- to address these issues. In GRAND, we first design a random propagation strategy to perform graph data augmentation. Then we leverage consistency regularization to optimize the prediction consistency of unlabeled nodes across different data augmentations. Extensive experiments on graph benchmark datasets suggest that GRAND significantly outperforms state-of-the-art GNN baselines on semi-supervised node classification. Finally, we show that GRAND mitigates the issues of over-smoothing and non-robustness, exhibiting better generalization behavior than existing GNNs. The source code of GRAND is publicly available at https://github.com/Grand20/grand.

cs.LG↗

arXiv2021

LUAI Challenge 2021 on Learning to Understand Aerial Images

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.

cs.CV↗

arXiv2021

Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation

Knowledge graphs (KGs) have proven to be effective for high-quality recommendation, where the connectivities between users and items provide rich and complementary information to user-item interactions. Most existing methods, however, are insufficient to exploit the KGs for capturing user preferences, as they either represent the user-item connectivities via paths with limited expressiveness or implicitly model them by propagating information over the entire KG with inevitable noise. In this paper, we design a novel hierarchical attentive knowledge graph embedding (HAKG) framework to exploit the KGs for effective recommendation. Specifically, HAKG first extracts the expressive subgraphs that link user-item pairs to characterize their connectivities, which accommodate both the semantics and topology of KGs. The subgraphs are then encoded via a hierarchical attentive subgraph encoding to generate effective subgraph embeddings for enhanced user preference prediction. Extensive experiments show the superiority of HAKG against state-of-the-art recommendation methods, as well as its potential in alleviating the data sparsity issue.

cs.IR↗

arXiv2021

Ohm-GPU: Integrating New Optical Network and Heterogeneous Memory into GPU Multi-Processors

Traditional graphics processing units (GPUs) suffer from the low memory capacity and demand for high memory bandwidth. To address these challenges, we propose Ohm-GPU, a new optical network based heterogeneous memory design for GPUs. Specifically, Ohm-GPU can expand the memory capacity by combing a set of high-density 3D XPoint and DRAM modules as heterogeneous memory. To prevent memory channels from throttling throughput of GPU memory system, Ohm-GPU replaces the electrical lanes in the traditional memory channel with a high-performance optical network. However, the hybrid memory can introduce frequent data migrations between DRAM and 3D XPoint, which can unfortunately occupy the memory channel and increase the optical network traffic. To prevent the intensive data migrations from blocking normal memory services, Ohm-GPU revises the existing memory controller and designs a new optical network infrastructure, which enables the memory channel to serve the data migrations and memory requests, in parallel. Our evaluation results reveal that Ohm-GPU can improve the performance by 181% and 27%, compared to a DRAM-based GPU memory system and the baseline optical network based heterogeneous memory system, respectively.

cs.AR↗

arXiv2021

Contact force measurements and local anisotropy in ellipses and disks

Experimental measurements of contact forces are limited to spheres and disks in three and two dimensions, making the evaluation of the shape effect and universality of force distributions and the comparison between experiments and theories extremely difficult. Here we present precise measurements of vector contact forces in photoelastic ellipses and disks subject to isotropic compression and pure shear. We find the local, instead of the global, stress ratio, control the width of the force distributions for forces larger than the mean, regardless of the particle shape and preparation protocols. By taking advantage of the anisotropic particle shape, we can determine the anisotropic growth of contacts in ellipses subject to isotropic compression, revealing the role of non-affine particle motions in homogenizing force distributions. Our results uncover the role of local anisotropy in the statistical framework of granular materials and open a new regime of exploring the role of particle shape on the mechanical and dynamical properties of granular materials in depth.

cond-mat.soft↗

arXiv2021

Stable and scalable multistage terahertz-driven particle accelerator

Particle accelerators that use electromagnetic fields to increase a charged particle's energy have greatly advanced the development of science and industry since invention. However, the enormous cost and size of conventional radio-frequency accelerators have limited their accessibility. Here we demonstrate a mini-accelerator powered by terahertz pulses with wavelengths 100 times shorter than radio-frequency pulses. By injecting a short relativistic electron bunch to a 30-mm-long dielectric-lined waveguide and tuning the frequency of a 20-period terahertz pulse to the phase-velocity-matched value, precise and sustained acceleration for nearly 100% of the electrons is achieved with the beam energy spread essentially unchanged. Furthermore, by accurately controlling the phase of two terahertz pulses, the beam is stably accelerated successively in two dielectric waveguides with close to 100% charge coupling efficiency. Our results demonstrate stable and scalable beam acceleration in a multistage mini-accelerator and pave the way for functioning terahertz-driven high-energy accelerators.

physics.acc-ph↗

arXiv2021

Correlated Oxide Dirac Semimetal in the Extreme Quantum Limit

Quantum materials (QMs) with strong correlation and non-trivial topology are indispensable to next-generation information and computing technologies. Exploitation of topological band structure is an ideal starting point to realize correlated topological QMs. Herein, we report that strain-induced symmetry modification in correlated oxide SrNbO3 thin films creates an emerging topological band structure. Dirac electrons in strained SrNbO3 films reveal ultra-high mobility (100,000 cm2/Vs), exceptionally small effective mass (0.04me), and non-zero Berry phase. More importantly, strained SrNbO3 films reach the extreme quantum limit, exhibiting a sign of fractional occupation of Landau levels and giant mass enhancement. Our results suggest that symmetry-modified SrNbO3 is a rare example of a correlated topological QM, in which strong correlation of Dirac electrons leads to the realization of fractional occupation of Landau levels.

cond-mat.str-el↗

arXiv2021

Meta Gradient Adversarial Attack

In recent years, research on adversarial attacks has become a hot spot. Although current literature on the transfer-based adversarial attack has achieved promising results for improving the transferability to unseen black-box models, it still leaves a long way to go. Inspired by the idea of meta-learning, this paper proposes a novel architecture called Meta Gradient Adversarial Attack (MGAA), which is plug-and-play and can be integrated with any existing gradient-based attack method for improving the cross-model transferability. Specifically, we randomly sample multiple models from a model zoo to compose different tasks and iteratively simulate a white-box attack and a black-box attack in each task. By narrowing the gap between the gradient directions in white-box and black-box attacks, the transferability of adversarial examples on the black-box setting can be improved. Extensive experiments on the CIFAR10 and ImageNet datasets show that our architecture outperforms the state-of-the-art methods for both black-box and white-box attack settings.

cs.CV↗

arXiv2021

M6-T: Exploring Sparse Expert Models and Beyond

Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost, and thus it has become a trend in model scaling. Still it is a mystery how MoE layers bring quality gains by leveraging the parameters with sparse activation. In this work, we investigate several key factors in sparse expert models. We observe that load imbalance may not be a significant problem affecting model quality, contrary to the perspectives of recent studies, while the number of sparsely activated experts $k$ and expert capacity $C$ in top-$k$ routing can significantly make a difference in this context. Furthermore, we take a step forward to propose a simple method called expert prototyping that splits experts into different prototypes and applies $k$ top-$1$ routing. This strategy improves the model quality but maintains constant computational costs, and our further exploration on extremely large-scale models reflects that it is more effective in training larger models. We push the model scale to over $1$ trillion parameters and implement it on solely $480$ NVIDIA V100-32GB GPUs, in comparison with the recent SOTAs on $2048$ TPU cores. The proposed giant model achieves substantial speedup in convergence over the same-size baseline.

cs.LG↗

arXiv2021

Exploring Structure Consistency for Deep Model Watermarking

The intellectual property (IP) of Deep neural networks (DNNs) can be easily ``stolen'' by surrogate model attack. There has been significant progress in solutions to protect the IP of DNN models in classification tasks. However, little attention has been devoted to the protection of DNNs in image processing tasks. By utilizing consistent invisible spatial watermarks, one recent work first considered model watermarking for deep image processing networks and demonstrated its efficacy in many downstream tasks. Nevertheless, it highly depends on the hypothesis that the embedded watermarks in the network outputs are consistent. When the attacker uses some common data augmentation attacks (e.g., rotate, crop, and resize) during surrogate model training, it will totally fail because the underlying watermark consistency is destroyed. To mitigate this issue, we propose a new watermarking methodology, namely ``structure consistency'', based on which a new deep structure-aligned model watermarking algorithm is designed. Specifically, the embedded watermarks are designed to be aligned with physically consistent image structures, such as edges or semantic regions. Experiments demonstrate that our method is much more robust than the baseline method in resisting data augmentation attacks for model IP protection. Besides that, we further test the generalization ability and robustness of our method to a broader range of circumvention attacks.

cs.CR↗

arXiv2021

Influence of Roughness on Granular Avalanches

Combining X-ray tomography with simultaneous shear force measurement, we investigate shear-induced granular avalanches using spherical particles with different surface roughness. We find that systems consisting of particles with large surface roughness display quasi-periodic avalanches interrupted by crackling-like small ones. In contrast, systems consisting of particles with small roughness display no detectable avalanches. The stress drop of quasi-periodic avalanche shows a linear relation with the correlation length of particle non-affine displacement, suggesting that roughness enhances inter-particle locking and hence particle-level dynamic correlation length. However, the nonaffine displacement is two orders of magnitude smaller than particle size, indicating that stress is mainly released on the length scale of roughness. The correlation length of non-affine displacements abruptly increases when a quasi-periodic avalanche occurs, suggesting that quasi-periodic avalanches can be interpreted as a spinodal nucleation event in a first-order phase transition.

cond-mat.soft↗

arXiv2021

Locality-aware Channel-wise Dropout for Occluded Face Recognition

Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as a useful approach. However, these artificial occlusions are commonly generated by adding a black rectangle or several object templates including sunglasses, scarfs and phones, which cannot well simulate the realistic occlusions. In this paper, based on the argument that the occlusion essentially damages a group of neurons, we propose a novel and elegant occlusion-simulation method via dropping the activations of a group of neurons in some elaborately selected channel. Specifically, we first employ a spatial regularization to encourage each feature channel to respond to local and different face regions. In this way, the activations affected by an occlusion in a local region are more likely to be located in a single feature channel. Then, the locality-aware channel-wise dropout (LCD) is designed to simulate the occlusion by dropping out the entire feature channel. Furthermore, by randomly dropping out several feature channels, our method can well simulate the occlusion of larger area. The proposed LCD can encourage its succeeding layers to minimize the intra-class feature variance caused by occlusions, thus leading to improved robustness against occlusion. In addition, we design an auxiliary spatial attention module by learning a channel-wise attention vector to reweight the feature channels, which improves the contributions of non-occluded regions. Extensive experiments on various benchmarks show that the proposed method outperforms state-of-the-art methods with a remarkable improvement.

cs.CV↗

arXiv2021

Supply Chain Digital Twin Framework Design: An Approach of Supply Chain Operations Reference Model and System of Systems

Digital twin technology has been regarded as a beneficial approach in supply chain development. Different from traditional digital twin (temporal dynamic), supply chain digital twin is a spatio-temporal dynamic system. This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue. A supply chain digital twin framework is developed based on the theories of system of systems and supply chain operations reference model. This framework is universal and can be applied in various types of supply chain systems. We firstly decompose the supply chain system into unified standard blocks preparing for the adoption of digital twin. Next, the idea of supply chain operations reference model is adopted to digitise basic supply chain activities within each block and explain how to use existing information system. Then, individual sub-digital twin is established for each member in supply chain system. After that, we apply the concept of system of systems to integrate and coordinate sub-digital twin into supply chain digital twin from the views of supply chain business integration and information system integration. At last, one simple supply chain system is applied to illustrate the application of the proposed model.

eess.SY↗

arXiv2021

Impact of Rotary-Wing UAV Wobbling on Millimeter-wave Air-to-Ground Wireless Channel

Millimeter-wave rotary-wing (RW) unmanned aerial vehicle (UAV) air-to-ground (A2G) links face unpredictable Doppler effect arising from the inevitable wobbling of RW UAV. Moreover, the time-varying channel characteristics during transmission lead to inaccurate channel estimation, which in turn results in the deteriorated bit error probability performance of the UAV A2G link. This paper studies the impact of mechanical wobbling on the Doppler effect of the millimeter-wave wireless channel between a hovering RW UAV and a ground node. Our contributions of this paper lie in: i) modeling the wobbling process of a hovering RW UAV; ii) developing an analytical model to derive the channel temporal autocorrelation function (ACF) for the millimeter-wave RW UAV A2G link in a closed-form expression; and iii) investigating how RW UAV wobbling impacts the Doppler effect on the millimeter-wave RW UAV A2G link. Numerical results show that different RW UAV wobbling patterns impact the amplitude and the frequency of ACF oscillation in the millimeter-wave RW UAV A2G link. For UAV wobbling, the channel temporal ACF decreases quickly and the impact of the Doppler effect is significant on the millimeter-wave A2G link.

eess.SP↗

arXiv2021

Optical manipulation of electronic dimensionality in a quantum material

Exotic phenomenon can be achieved in quantum materials by confining electronic states into two dimensions. For example, relativistic fermions are realised in a single layer of carbon atoms, the quantized Hall effect can result from two-dimensional (2D) systems, and the superconducting transition temperature can be enhanced significantly in a one-atomic-layer material. Ordinarily, 2D electronic system can be obtained by exfoliating the layered materials, growing monolayer materials on substrates, or establishing interfaces between different materials. Herein, we use femtosecond infrared laser pulses to invert the periodic lattice distortion sectionally in a three-dimensional (3D) charge density wave material, creating macroscopic domain walls of transient 2D ordered electronic states with exotic properties. The corresponding ultrafast electronic and lattice dynamics are captured by time- and angle-resolved photoemission spectroscopy and MeV ultrafast electron diffraction. Surprisingly, a novel energy gap state, which might be a signature of light-induced superconductivity, is identified in the photoinduced 2D domain wall near the surface. Such optical modulation of atomic motion is a new path to realise 2D electronic states and will be a new platform for creating novel phases in quantum materials.

cond-mat.str-el↗