Searcharxiv⌕ Search

arXiv subjects

Junwei Zhang

Publications and source records attributed to Junwei Zhang.

At least 55 records · Page 3Linked to original sources
arXiv2021

Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation

Generative Adversarial Networks (GAN) is an adversarial model, and it has been demonstrated to be effective for various generative tasks. However, GAN and its variants also suffer from many training problems, such as mode collapse and gradient vanish. In this paper, we firstly propose a general crossover operator, which can be widely applied to GANs using evolutionary strategies. Then we design an evolutionary GAN framework C-GAN based on it. And we combine the crossover operator with evolutionary generative adversarial networks (EGAN) to implement the evolutionary generative adversarial networks with crossover (CE-GAN). Under the premise that a variety of loss functions are used as mutation operators to generate mutation individuals, we evaluate the generated samples and allow the mutation individuals to learn experiences from the output in a knowledge distillation manner, imitating the best output outcome, resulting in better offspring. Then, we greedily selected the best offspring as parents for subsequent training using discriminator as evaluator. Experiments on real datasets demonstrate the effectiveness of CE-GAN and show that our method is competitive in terms of generated images quality and time efficiency.

cs.LG↗
arXiv2020

Proximal Policy Optimization via Enhanced Exploration Efficiency

Proximal policy optimization (PPO) algorithm is a deep reinforcement learning algorithm with outstanding performance, especially in continuous control tasks. But the performance of this method is still affected by its exploration ability. For classical reinforcement learning, there are some schemes that make exploration more full and balanced with data exploitation, but they can't be applied in complex environments due to the complexity of algorithm. Based on continuous control tasks with dense reward, this paper analyzes the assumption of the original Gaussian action exploration mechanism in PPO algorithm, and clarifies the influence of exploration ability on performance. Afterward, aiming at the problem of exploration, an exploration enhancement mechanism based on uncertainty estimation is designed in this paper. Then, we apply exploration enhancement theory to PPO algorithm and propose the proximal policy optimization algorithm with intrinsic exploration module (IEM-PPO) which can be used in complex environments. In the experimental parts, we evaluate our method on multiple tasks of MuJoCo physical simulator, and compare IEM-PPO algorithm with curiosity driven exploration algorithm (ICM-PPO) and original algorithm (PPO). The experimental results demonstrate that IEM-PPO algorithm needs longer training time, but performs better in terms of sample efficiency and cumulative reward, and has stability and robustness.

cs.LG↗
arXiv2020

Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective

Recommender systems (RSs) now play a very important role in the online lives of people as they serve as personalized filters for users to find relevant items from an array of options. Owing to their effectiveness, RSs have been widely employed in consumer-oriented e-commerce platforms. However, despite their empirical successes, these systems still suffer from two limitations: data noise and data sparsity. In recent years, generative adversarial networks (GANs) have garnered increased interest in many fields, owing to their strong capacity to learn complex real data distributions; their abilities to enhance RSs by tackling the challenges these systems exhibit have also been demonstrated in numerous studies. In general, two lines of research have been conducted, and their common ideas can be summarized as follows: (1) for the data noise issue, adversarial perturbations and adversarial sampling-based training often serve as a solution; (2) for the data sparsity issue, data augmentation--implemented by capturing the distribution of real data under the minimax framework--is the primary coping strategy. To gain a comprehensive understanding of these research efforts, we review the corresponding studies and models, organizing them from a problem-driven perspective. More specifically, we propose a taxonomy of these models, along with their detailed descriptions and advantages. Finally, we elaborate on several open issues and current trends in GAN-based RSs.

cs.IR↗
arXiv2020

Path-Based Reasoning over Heterogeneous Networks for Recommendation via Bidirectional Modeling

Heterogeneous Information Network (HIN) is a natural and general representation of data in recommender systems. Combining HIN and recommender systems can not only help model user behaviors but also make the recommendation results explainable by aligning the users/items with various types of entities in the network. Over the past few years, path-based reasoning models have shown great capacity in HIN-based recommendation. The basic idea of these models is to explore HIN with predefined path schemes. Despite their effectiveness, these models are often confronted with the following limitations: (1) Most prior path-based reasoning models only consider the influence of the predecessors on the subsequent nodes when modeling the sequences, and ignore the reciprocity between the nodes in a path; (2) The weights of nodes in the same path instance are usually assumed to be constant, whereas varied weights of nodes can bring more flexibility and lead to expressive modeling; (3) User-item interactions are noisy, but they are often indiscriminately exploited. To overcome the aforementioned issues, in this paper, we propose a novel path-based reasoning approach for recommendation over HIN. Concretely, we use a bidirectional LSTM to enable the two-way modeling of paths and capture the reciprocity between nodes. Then an attention mechanism is employed to learn the dynamical influence of nodes in different contexts. Finally, the adversarial regularization terms are imposed on the loss function of the model to mitigate the effects of noise and enhance HIN-based recommendation. Extensive experiments conducted on three public datasets show that our model outperforms the state-of-the-art baselines. The case study further demonstrates the feasibility of our model on the explainable recommendation task.

cs.IR↗
arXiv2020

ScenarioSA: A Large Scale Conversational Database for Interactive Sentiment Analysis

Interactive sentiment analysis is an emerging, yet challenging, subtask of the sentiment analysis problem. It aims to discover the affective state and sentimental change of each person in a conversation. Existing sentiment analysis approaches are insufficient in modelling the interactions among people. However, the development of new approaches are critically limited by the lack of labelled interactive sentiment datasets. In this paper, we present a new conversational emotion database that we have created and made publically available, namely ScenarioSA. We manually label 2,214 multi-turn English conversations collected from natural contexts. In comparison with existing sentiment datasets, ScenarioSA (1) covers a wide range of scenarios; (2) describes the interactions between two speakers; and (3) reflects the sentimental evolution of each speaker over the course of a conversation. Finally, we evaluate various state-of-the-art algorithms on ScenarioSA, demonstrating the need of novel interactive sentiment analysis models and the potential of ScenarioSA to facilitate the development of such models.

cs.IR↗
arXiv2020

Thermally induced generation and annihilation of magnetic chiral skyrmion bubbles and achiral bubbles in Mn-Ni-Ga Magnets

Magnetic chiral skyrmion bubbles and achiral bubbles are two independent magnetic domain structures, in which the former with equivalent winding number to skyrmions offers great promise as information carriers for further spintronic devices. Here, in this work, we experimentally investigate the generation and annihilation of magnetic chiral skyrmion bubbles and achiral bubbles in the Mn-Ni-Ga thin plate by using the Lorentz transmission electron microscopy (L-TEM). The two independent magnetic domain structures can be directly controlled after the field cooling manipulation by varying the titled angles of external magnetic fields. By imaging the magnetization reversal with increasing temperature, we found an extraordinary annihilation mode of magnetic chiral skyrmion bubbles and a non-linear frequency for the winding number reversal. Quantitative analysis of such dynamics was performed by using L-TEM to directly determine the barrier energy for the magnetization reversal of magnetic chiral skyrmion bubbles.

cond-mat.mtrl-sci↗
arXiv2020

Néel-type skyrmion in WTe2/Fe3GeTe2 van der Waals heterostructure

The promise of high-density and low-energy-consumption devices motivates the search for layered structures that stabilize chiral spin textures such as topologically protected skyrmions. At the same time, layered structures provide a new platform for the discovery of new physics and effects. Recently discovered long-range intrinsic magnetic orders in the two-dimensional van der Waals materials offer new opportunities. Here we demonstrate the Dzyaloshinskii-Moriya interaction and Néel-type skyrmions are induced at the WTe2/Fe3GeTe2 interface. Fe3GeTe2 is a ferromagnetic material with strong perpendicular magnetic anisotropy. We demonstrate that the strong spin orbit interaction in 1T'-WTe2 does induce a large interfacial Dzyaloshinskii-Moriya interaction at the interface with Fe3GeTe2 due to the inversion symmetry breaking to stabilize skyrmions. Transport measurements show the topological Hall effect in this heterostructure for temperatures below 100 K. Furthermore, Lorentz transmission electron microscopy is used to directly image Néel-type skyrmions along with aligned and stripe-like domain structure. This interfacial coupling induced Dzyaloshinskii-Moriya interaction is estimated to have a large energy of 1.0 mJ/m^2, which can stabilize the Néel-type skyrmions in this heterostructure. This work paves a path towards the skyrmionic devices based on van der Waals heterostructures.

cond-mat.mtrl-sci↗
arXiv2019

Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning

Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters setting and needs efficient exploration; Evolutionary algorithms are stable, but with low sample efficiency; Imitation learning is both sample efficient and stable, however it requires the guidance of expert data. In this paper, we propose Recruitment-imitation Mechanism (RIM) for evolutionary reinforcement learning, a scalable framework that combines advantages of the three methods mentioned above. The core of this framework is a dual-actors and single critic reinforcement learning agent. This agent can recruit high-fitness actors from the population of evolutionary algorithms, which instructs itself to learn from experience replay buffer. At the same time, low-fitness actors in the evolutionary population can imitate behavior patterns of the reinforcement learning agent and improve their adaptability. Reinforcement and imitation learners in this framework can be replaced with any off-policy actor-critic reinforcement learner or data-driven imitation learner. We evaluate RIM on a series of benchmarks for continuous control tasks in Mujoco. The experimental results show that RIM outperforms prior evolutionary or reinforcement learning methods. The performance of RIM's components is significantly better than components of previous evolutionary reinforcement learning algorithm, and the recruitment using soft update enables reinforcement learning agent to learn faster than that using hard update.

cs.LG↗
arXiv2019

Topological Hall effect in bulk ferromagnet Cr$_2$Te$_3$ embedded with black-phosphorus-like bismuth nanosheets

We implement the molecular beam epitaxy method to embed the black-phosphorus-like bismuth nanosheets into the bulk ferromagnet Cr$_2$Te$_3$. As a typical surfactant, bismuth lowers the surface tensions and mediates the layer-by-layer growth of Cr$_2$Te$_3$. Meanwhile, the bismuth atoms precipitate into black-phosphorus-like nanosheets with the lateral size of several tens of nanometers. In Cr$_2$Te$_3$ embedded with Bi-nanosheets, we observe simultaneously a large topological Hall effect together with the magnetic susceptibility plateau and magnetoresistivity anomaly. As a control experiment, none of these signals is observed in the pristine Cr$_2$Te$_3$ samples. Therefore, the Bi-nanosheets serve as seeds of topological Hall effect induced by non-coplanar magnetic textures planted into Cr$_2$Te$_3$. Our experiments demonstrate a new method to generates a large topological Hall effect by planting strong spin-orbit couplings into the traditional ferromagnet, which may have potential applications in spintronics.

cond-mat.mtrl-sci↗
arXiv2019

Current-driven magnetization switching in a van der Waals ferromagnet Fe3GeTe2

The recent discovery of ferromagnetism in two-dimensional (2D) van der Waals (vdW) materials holds promises for novel spintronic devices with exceptional performances. However, in order to utilize 2D vdW magnets for building spintronic nanodevices such as magnetic memories, key challenges remain in terms of effectively switching the magnetization from one state to the other electrically. Here, we devise a bilayer structure of Fe3GeTe2/Pt, in which the magnetization of few-layered Fe3GeTe2 can be effectively switched by the spin-orbit torques (SOTs) originated from the current flowing in the Pt layer. The effective magnetic fields corresponding to the SOTs are further quantitatively characterized using harmonic measurements. Our demonstration of the SOT-driven magnetization switching in a 2D vdW magnet could pave the way for implementing low-dimensional materials in the next-generation spintronic applications.

cond-mat.mes-hall↗
arXiv2018

Coflow Scheduling in Data Centers: Routing and Bandwidth Allocation

In distributed computing frameworks like MapReduce, Spark, and Dyrad, a coflow is a set of flows transferring data between two stages of a job. The job cannot start its next stage unless all flows in the coflow finish. To improve the execution performance of such a job, it is crucial to reduce the completion time of a coflow which can contribute more than 50% of the job completion time. While several schedulers have been proposed, we observe that routing, as a factor greatly impacting the Coflow Completion Time (CCT), has not been well considered. In this paper, we focus on the coflow scheduling problem and jointly consider routing and bandwidth allocation. We first provide an analytical solution to the problem of optimal bandwidth allocation with pre-determined routes. We then formulate the coflow scheduling problem as a Mixed Integer Non-linear Programming problem and present its relaxed convex optimization problem. We further propose two algorithms, CoRBA and its simplified version: CoRBA-fast, that jointly perform routing and bandwidth allocation for a given coflow while minimizes the CCT. Through both offline and online simulations, we demonstrate that CoRBA reduces the CCT by 40%-500% compared to the state-of-the-art algorithms. Simulation results also show that CoRBA-fast can be tens of times faster than all other algorithms with around 10% performance degradation compared to CoRBA, which makes the use of CoRBA-fast very applicable in practice.

cs.NI↗
arXiv2018

Layer Based Partition for Matrix Multiplication on Heterogeneous Processor Platforms

While many approaches have been proposed to analyze the problem of matrix multiplication parallel computing, few of them address the problem on heterogeneous processor platforms. It still remains an open question on heterogeneous processor platforms to find the optimal schedule that balances the load within the heterogeneous processor set while minimizing the amount of communication. A great many studies are based on rectangular partition, whereas the optimality of rectangular partition as the basis has not been well justified. In this paper, we propose a new method that schedules matrix multiplication on heterogeneous processor platforms with the mixed co-design goal of minimizing the total communication volume and the multiplication completion time. We first present the schema of our layer based partition (LBP) method. Subsequently, we demonstrate that our approach guarantees minimal communication volume, which is smaller than what rectangular partition can reach. We further analyze the problem of minimizing the task completion time, with network topologies taken into account. We solve this problem in both single-neighbor network case and multi-neighbor network case. In single-neighbor network cases, we propose an equality based method to solve LBP, and simulation shows that the total communication volume is reduced by 75% from the lower bound of rectangular partition. In multi-neighbor network cases, we formulate LBP as a Mixed Integer Programming problem, and reduce the total communication volume by 81% through simulation. To summarize, this is a promising perspective of tackling matrix multiplication problems on heterogeneous processor platforms.

cs.NI↗
arXiv2018

Giant Planar Hall Effect in the Dirac Semimetal ZrTe5

Recently, giant planar Hall effect originating from chiral anomaly has been predicted in nonmagnetic Dirac/Weyl semimetals. ZrTe5 is considered to be an intriguing Dirac semimetal at the boundary of weak topological insulators and strong topological insulators, though this claim still remains controversial. Here, we report the observation in ZrTe5 of the giant planar Hall resistivity that shows two different magnetic-field dependences as predicted by theory and a maximum at the Lifshitz transition temperature. We found that the giant planar Hall resistivity fades out with decreasing the thickness of ZrTe5 nanoplates, which may be ascribed to the vanishing of the 3D nature of the samples. In addition, we have observed a nontrivial Berry phase, chiral-anomaly-induced negative longitudinal magnetoresistance, and a giant in-plane anisotropic magnetoresistance in these ZrTe5 nanoplates. All the experimental observations demonstrated coherently that ZrTe5 is a Dirac semimetal.

cond-mat.mes-hall↗
arXiv2018

Thermally assisted skyrmions creation in Pt/Co/Ta multilayer films

Néel-type magnetic skyrmions in multilayer films have attracted significant amount of attention recently for their stability at room temperature and capability of motion driven by a low-density electrical current, which can be potentially applied to spintronic devices. However, the thermal effect on the formation of the skyrmions and their behavior has rarely been studied. Here, we report a study on the creation of skyrmions in [Pt/Co/Ta]10 multilayer samples at different temperatures using an in-situ Lorentz transmission electron microscopy. By imaging the magnetization reversal process from positive (negative) saturation to negative (positive) saturation, we found that the skyrmions can be created by nucleation from ferromagnetic saturation state and by breaking the labyrinth domains under certain external fields. By tuning the external fields, a maximum density of skyrmions was reached at different temperatures. The key finding is that the creation of the skyrmions in the multilayers depends critically on the temperature and thermal history.

cond-mat.mes-hall↗
arXiv2018

Determination of chirality and density control of Néel-type skyrmions with in-plane magnetic field

Magnetic skyrmions are topologically protected nanoscale spin textures exhibiting fascinating physical behaviors. Recent observations of room temperature Néel-type skyrmions in magnetic multilayer films are an important step towards their use in ultra-low power devices. We have investigated the magnetization reversal in a [Pt/Co/Ta]11 multilayer sample under a tilted magnetic field using the in-situ Lorentz tunneling electron microscopy. On decreasing the magnetic field individual skyrmions appear that subsequently evolve into snake-like structures growing in the direction opposite to the in-plane magnetic field. We show that this unusual relation between the velocity vector and the magnetic field is dominated by the chirality of the Néel-type skyrmions. It allows one to extract the sign of the Dzyaloshinskii-Moriya constant. We also demonstrate that high concentration of skyrmions can be achieved on increasing the in-plane component of the field. Our micromagnetic simulations agree with our experimental results.

cond-mat.mes-hall↗
arXiv2017

Orbital-angular-momentum mode-group multiplexed transmission over a graded-index ring-core fiber based on receive diversity and maximal ratio combining

An orbital-angular-momentum (OAM) mode-group multiplexing (MGM) scheme based on a graded-index ring-core fiber (GIRCF) is proposed, in which a single-input two-output (or receive diversity) architecture is designed for each MG channel and simple digital signal processing (DSP) is utilized to adaptively resist the mode partition noise resulting from random intra-group mode crosstalk. There is no need of complex multiple-input multiple-output (MIMO) equalization in this scheme. Furthermore, the signal-to-noise ratio (SNR) of the received signals can be improved if a simple maximal ratio combining (MRC) technique is employed on the receiver side to efficiently take advantage of the diversity gain of receiver. Intensity-modulated direct-detection (IM-DD) systems transmitting three OAM mode groups with total 100-Gb/s discrete multi-tone (DMT) signals over a 1-km GIRCF and two OAM mode groups with total 40-Gb/s DMT signals over an 18-km GIRCF are experimentally demonstrated, respectively, to confirm the feasibility of our proposed OAM-MGM scheme.

eess.SP↗
arXiv2015

Space Filling Curves for 3D Sensor Networks with Complex Topology

Several aspects of managing a sensor network (e.g., motion planning for data mules, serial data fusion and inference) benefit once the network is linearized to a path. The linearization is often achieved by constructing a space filling curve in the domain. However, existing methods cannot handle networks distributed on surfaces of complex topology. This paper presents a novel method for generating space filling curves for 3D sensor networks that are distributed densely on some two-dimensional geometric surface. Our algorithm is completely distributed and constructs a path which gets uniformly, progressively denser as it becomes longer. We analyze the algorithm mathematically and prove that the curve we obtain is dense. Our method is based on the Hodge decomposition theorem and uses holomorphic differentials on Riemann surfaces. The underlying high genus surface is conformally mapped to a union of flat tori and then a proportionally-dense space filling curve on this union is constructed. The pullback of this curve to the original network gives us the desired curve.

cs.CG↗