arXiv subjects

Yuan He

Publications and source records attributed to Yuan He.

At least 163 records · Page 9Linked to original sources

arXiv2020

Self-supervised Adversarial Training

Recent work has demonstrated that neural networks are vulnerable to adversarial examples. To escape from the predicament, many works try to harden the model in various ways, in which adversarial training is an effective way which learns robust feature representation so as to resist adversarial attacks. Meanwhile, the self-supervised learning aims to learn robust and semantic embedding from data itself. With these views, we introduce self-supervised learning to against adversarial examples in this paper. Specifically, the self-supervised representation coupled with k-Nearest Neighbour is proposed for classification. To further strengthen the defense ability, self-supervised adversarial training is proposed, which maximizes the mutual information between the representations of original examples and the corresponding adversarial examples. Experimental results show that the self-supervised representation outperforms its supervised version in respect of robustness and self-supervised adversarial training can further improve the defense ability efficiently.

cs.LG↗

arXiv2019

AdvKnn: Adversarial Attacks On K-Nearest Neighbor Classifiers With Approximate Gradients

Deep neural networks have been shown to be vulnerable to adversarial examples---maliciously crafted examples that can trigger the target model to misbehave by adding imperceptible perturbations. Existing attack methods for k-nearest neighbor~(kNN) based algorithms either require large perturbations or are not applicable for large k. To handle this problem, this paper proposes a new method called AdvKNN for evaluating the adversarial robustness of kNN-based models. Firstly, we propose a deep kNN block to approximate the output of kNN methods, which is differentiable thus can provide gradients for attacks to cross the decision boundary with small distortions. Second, a new consistency learning for distribution instead of classification is proposed for the effectiveness in distribution based methods. Extensive experimental results indicate that the proposed method significantly outperforms state of the art in terms of attack success rate and the added perturbations.

cs.CV↗

arXiv2019

Graph Neural Networks for Social Recommendation

In recent years, Graph Neural Networks (GNNs), which can naturally integrate node information and topological structure, have been demonstrated to be powerful in learning on graph data. These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key. However, building social recommender systems based on GNNs faces challenges. For example, the user-item graph encodes both interactions and their associated opinions; social relations have heterogeneous strengths; users involve in two graphs (e.g., the user-user social graph and the user-item graph). To address the three aforementioned challenges simultaneously, in this paper, we present a novel graph neural network framework (GraphRec) for social recommendations. In particular, we provide a principled approach to jointly capture interactions and opinions in the user-item graph and propose the framework GraphRec, which coherently models two graphs and heterogeneous strengths. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework GraphRec. Our code is available at \url{https://github.com/wenqifan03/GraphRec-WWW19}

cs.IR↗

arXiv2019

Learning To Characterize Adversarial Subspaces

Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of \textit{adversarial subspaces} where adversarial examples lie. However, we find these methods are not working in practical attack detection scenarios. Because the artificially defined features are lack of robustness and show limitation in discriminative power to detect strong attacks. To solve this problem, we propose a novel adversarial detection method which identifies adversaries by adaptively learning reasonable metrics to characterize adversarial subspaces. As auxiliary context information, \textit{k} nearest neighbors are used to represent the surrounded subspace of the detected sample. We propose an innovative model called Neighbor Context Encoder (NCE) to learn from \textit{k} neighbors context and infer if the detected sample is normal or adversarial. We conduct thorough experiment on CIFAR-10, CIFAR-100 and ImageNet dataset. The results demonstrate that our approach surpasses all existing methods under three settings: \textit{attack-aware black-box detection}, \textit{attack-unaware black-box detection} and \textit{white-box detection}.

cs.CV↗

arXiv2019

Robust edge photocurrent response on layered Type II Weyl semimetal WTe2

Photo sensing and energy harvesting based on exotic properties of quantum materials and new operation principles have great potentials to break the fundamental performance limit of conventional photodetectors and solar cells. As topological nontrivial materials, Weyl semimetals have demonstrated novel optoelectronic properties that promise potential applications in photo detection and energy harvesting arising from their gapless linear dispersion near Weyl nodes and Berry field enhanced nonlinear optical effect at the vicinity of Weyl nodes. In this work, we demonstrate robust photocurrent generation from charge separation of photoexctied electron-hole pairs at the edge of Td-WTe2, a type-II Weyl semimetal, due to crystalline-symmetry breaking along certain crystal fracture directions and possibly enhanced by robust fermi-arc type surface states. Using scanning photocurrent microscopy (SPCM) measurements, we further demonstrate that the edge current response is robust over a wide excitation photon energy. We find that this robust feature is highly generic, and shall arise universally in a wide class of quantum materials with similar crystal symmetries. In addition, possible connections between these edge photocurrents and topological properties of Weyl semimetals are explored. The robust and generic edge current response demonstrated in this work provides a new type of charge separation mechanism for photosensing and energy harvesting over broad wavelength range.

cond-mat.mes-hall↗

arXiv2019

Superconductivity in the Ru-Doped CuIr2Te4 Telluride Chalcogenide

Here we report the effect of structural and superconductivity properties on Ru doped CuIr2Te4 telluride chalcogenide. XRD results suggest that the CuIr2-xRuxTe4 maintain the disordered trigonal structure with space group P3m1 (No. 164) for x less than 0.3. The lattice constants, a and c, both decrease with increasing Ru content. Temperature-dependent resistivity, magnetic susceptibility and specific-heat measurements are performed to characterize the superconducting properties systematically. Our results suggest that the optimal doping level for superconductivity in CuIr2-xRuxTe4 is x = 0.05, where Tc is 2.79 K with the Sommerfeld constant gamma of 11.52 mJ mol-1 K-2 and the specific-heat anomaly at the superconducting transition, is approximately 1.51, which is higher than the BCS value of 1.43, indicating CuIr1.95Ru0.05Te4 is a strongly electron-phonon coupled superconductor. The values of lower critical filed and upper critical field calculated from isothermal magnetization and magneto-transport measurements are 0.98 KOe and 2.47 KOe respectively, signifying that the compound is clearly a type-II superconductor. Finally, a dome-like shape superconducting Tcs vs. x content phase diagram is established, where the charge density wave disappears at x = 0.03 while superconducting transition temperature (Tc) rises until it reaches its peak at x = 0.05, then, with decreasing when x reaches 0.3. This feature of the competition between CDW and the superconductivity could be caused by tuning the Fermi surface and density of states with Ru chemical doping.

cond-mat.supr-con↗

arXiv2019

High CO2-tolerance oxygen permeation dual-phase membranes Ce0.9Pr0.1O2-δ-Pr0.6Sr0.4Fe0.8Al0.2O3-δ

High stability and oxygen permeability are two prominent requirements for the oxygen transport membrane candidates used as industrialization. Herein, we report several composite membranes based on xwt.%Ce0.9Pr0.1O2(CPO)-(100-x)wt.%Pr0.6Sr0.4Fe0.8Al0.2O3(PSFAO) (x = 50, 60 and 75) prepared via a modified Pechini method. Oxygen permeability test reveals that the 60CPO-40PSFAO composition exhibits the highest oxygen permeability. The oxygen permeation flux through the optimal uncoated 0.33 mm-thickness 60CPO-40PSFAO composite can reach 1.03 mL cm-2 min-1 (over the general requirement value of 1 mL cm-2 min-1) in air/He atmosphere at 1000 °C. In situ XRD performance confirms the optimal 60CPO-40PSFAO sample shows excellent stability in CO2-containing atmospheres. The 60CPO-40PSFAO membrane still exhibits simultaneously excellent oxygen permeability and phase stability after operating for over 100 h at air/CO2 condition at 1000 °C, which further indicates that the 60CPO-40PSFAO composite is likely to be used for oxygen supply in CO2 capture

physics.app-ph↗

arXiv2019

NbSeTe -A New Layered Transition Metal Dichalcogenide Superconductor

Transition metal dichalcogenides (TMDCs) usually exhibit layered polytypic structures due to the weak interlayer coupling. 2H-NbSe2 is one of the most widely studied in the pristine TMDC family due to its high superconducting transition temperature (Tc = 7.3K) and the occurrence of a charge-density wave (CDW) order below 33 K. The coexistence of CDW with superconductivity poses an intriguing open question about the relationship between Fermi surface nesting and Cooper pairing. Past studies of this issue have mostly been focused on doping 2H-NbSe2 by 3d transition metals without significantly changing its crystal structure. Here we replaced the Se by Te in 2H-NbSe2 in order to design a new 1T polytype layered TMDC NbSeTe, which adopts a trigonal structure with space group P-3m1. We successfully grew large size and high-quality single crystals of 1T-NbSeTe via the vapor transport method using I2 as the transport agent. Temperature-dependent resistivity and specific heat data revealed a bulk Tc at 1.3 K, which is the first observation of superconductivity in pure 1T-NbSeTe phase. This compound enlarged the family of superconducting TMDCs and provides an opportunity to study the interplay between CDW and superconductivity in the trigonal structure.

cond-mat.supr-con↗

arXiv2019

High-flux dual-phase percolation membrane for oxygen separation

A series of composites based on (100-x)wt.%Ce0.9Pr0.1O2-δ-xwt.%Pr0.6Ca0.4FeO3-δ (x = 25, 40 and 50) doped with the cheap and abundant alkaline earth metal Ca2+ at the A-site has been successfully designed and fabricated. The crystal structure, oxygen permeability, phase and CO2 stability were evaluated. The composition of 60wt.%Ce0.9Pr0.1O2-δ-40wt.%Pr0.6Ca0.4FeO3-δ(60CPO-40PCFO) possesses the highest oxygen permeability among three studied composites. At 1000 oC, the oxygen permeation fluxes through the 0.3 mm-thickness 60CPO-40PCFO membranes after porous La0.6Sr0.4CoO3-δ each to 1.00 mL cm-2 min-1 and 0.62 mL cm-2 min-1 under air/He and air/CO2 gradients, respectively. In situ XRD results demonstrated that the 60CPO-40PCFO sample displayed a perfect structural stability in air as well as CO2-containing atmosphere. Thus, low-cost, Co-free and Sr-free 60CPO-40PCFO has high CO2 stability and is economical and environmental friendly since the expensive and volatile element Co was replaced by Fe and Sr was waived since it easily forms carbonates.

physics.app-ph↗

arXiv2019

Effects of Al content on the oxygen permeability through dual-phase membrane 60Ce$_{0.9}$Pr$_{0.1}$O$_{2-δ}$-40Pr$_{0.6}$Sr$_{0.4}$Fe$_{1-x}$Al$_x$O$_{3-δ}$

Ceramic dual-phase oxygen transport membranes with the composition of 60wt.% Ce0.9Pr0.1O2-δ-40wt.%Pr0.6Sr0.4Fe1-xAlxO3-δ (x = 0.05, 0.1, 0.2, 0.3, 0.4, 0.6, 0.8, 1.0) (60CPO-40PSF1-xAxO) based on 60Ce0.9Pr0.1O2-δ-40Pr0.6Sr0.4FeO3-δ doped Al was successfully synthesized through a modified Pechini method. Crystal structure, surface microtopography and oxygen permeability are investigated systematically. The cell parameters of perovskite phase first increased and then decreased with the increase of Al content, which is related to the radius of the Al3+ and the formation of impurity phase. As x ranges from 0.1 to 0.8, the oxygen permeability of the materials first increases and then decreases, and the maximum value of oxygen permeation rate for 60CPO-40PSF1-xAxO membranes with 0.4mm thickness at 1000 °C is 1.12 mL min-1 cm-2 when x = 0.4. XRD measurements revealed high temperature stability and CO2-tolerant property of the dual-phase composites. The partial replacement of Fe$^{3+}$/Fe$^{4+}$ by Al$^{3+}$ causes the material not only to exhibit good stability, but also to increase the oxygen permeability of the membranes.

physics.app-ph↗

arXiv2019

The Unusual Suppression of Superconducting Transition Temperature in Double-Doping 2H-NbSe$_2$

2H-NbSe2 is one of the most widely researched transition metal dichalcogenide (TMD) superconductors, which undergoes charge-density wave (CDW) transition at TCDW about 33 K and superconducting transition at Tc of 7.3 K. To explore the relation between its superconductivity and Fermi surface nesting, we combined S substitution with Cu intercalation in 2H-NbSe2 to make CuxNbSe2-ySy. Upon systematic substitution of S and intercalation of Cu ions into 2H-NbSe2, we found that when the Cu and S contents increases, the Tc decreases in CuxNbSe2-ySy. While at higher x and y values, Tc keeps a constant value near 2 K, which is not commonly observed for a layered TMD. For comparison, we found the simultaneous substitution of Nb by Cu and Se by S in CuxNb1-xSe2-ySy lowered the Tc substantially faster. We construct a superconducting phase diagrams for our double-doping compounds in contrast with the related single-ions doping systems.

cond-mat.supr-con↗

arXiv2019

An Open-Source Benchmark Suite for Cloud and IoT Microservices

Cloud services have recently started undergoing a major shift from monolithic applications, to graphs of hundreds of loosely-coupled microservices. Microservices fundamentally change a lot of assumptions current cloud systems are designed with, and present both opportunities and challenges when optimizing for quality of service (QoS) and utilization. In this paper we explore the implications microservices have across the cloud system stack. We first present DeathStarBench, a novel, open-source benchmark suite built with microservices that is representative of large end-to-end services, modular and extensible. DeathStarBench includes a social network, a media service, an e-commerce site, a banking system, and IoT applications for coordination control of UAV swarms. We then use DeathStarBench to study the architectural characteristics of microservices, their implications in networking and operating systems, their challenges with respect to cluster management, and their trade-offs in terms of application design and programming frameworks. Finally, we explore the tail at scale effects of microservices in real deployments with hundreds of users, and highlight the increased pressure they put on performance predictability.

cs.DC↗

arXiv2019

Leveraging Deep Learning to Improve the Performance Predictability of Cloud Microservices

Performance unpredictability is a major roadblock towards cloud adoption, and has performance, cost, and revenue ramifications. Predictable performance is even more critical as cloud services transition from monolithic designs to microservices. Detecting QoS violations after they occur in systems with microservices results in long recovery times, as hotspots propagate and amplify across dependent services. We present Seer, an online cloud performance debugging system that leverages deep learning and the massive amount of tracing data cloud systems collect to learn spatial and temporal patterns that translate to QoS violations. Seer combines lightweight distributed RPC-level tracing, with detailed low-level hardware monitoring to signal an upcoming QoS violation, and diagnose the source of unpredictable performance. Once an imminent QoS violation is detected, Seer notifies the cluster manager to take action to avoid performance degradation altogether. We evaluate Seer both in local clusters, and in large-scale deployments of end-to-end applications built with microservices with hundreds of users. We show that Seer correctly anticipates QoS violations 91% of the time, and avoids the QoS violation to begin with in 84% of cases. Finally, we show that Seer can identify application-level design bugs, and provide insights on how to better architect microservices to achieve predictable performance.

cs.DC↗

arXiv2019

Fixed Region Beamforming using Frequency Diverse Subarray for Secure Mmwave Wireless Communications

Millimeter-wave (mmWave) using conventional phased array (CPA) enables highly directional and fixed angular beamforming (FAB), therefore enhancing physical layer security (PLS) in the angular domain. However, as the eavesdropper is located in the direction pointed by the mainlobe of the information-carrying beam, information leakage is inevitable and FAB cannot guarantee PLS performance. To address this threat, we propose a novel fixed region beamforming (FRB) by employing a frequency diverse subarray (FDSA) architecture to enhance the PLS performance for mmWave directional communications. In particular, we carefully introduce multiple frequency offset increments (FOIs) across subarrays to achieve a sophisticated beampattern synthesis that ensures a confined information transmission only within the desired angle-range region (DARR) in close vicinity of the target user. More specifically, we formulate the secrecy rate maximization problem with FRB over possible subarray FOIs, and consider two cases of interests, i.e., without/with the location information of eavesdropping, both turn out to be NP-hard. For the unknown eavesdropping location case, we propose a seeker optimization algorithm to minimize the maximum sidelobe peak of the beampattern outside the DARR. As for the known eavesdropping location case, a block coordinate descend linear approximation algorithm is proposed to minimize the sidelobe level in the eavesdropping region. By using the proposed FRB, the mainlobes of all subarrays are constructively superimposed in the DARR while the sidelobes are destructively overlayed outside the DARR. Therefore, FRB takes prominent effect on confining information transmission within the DARR. Numerical simulations demonstrate that the proposed FDSA-based FRB can provide superior PLS performance over the CPA-based FAB.

cs.IT↗

arXiv2019

Dual Encoding for Zero-Example Video Retrieval

This paper attacks the challenging problem of zero-example video retrieval. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described in natural language text with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is required. The majority of existing methods are concept based, extracting relevant concepts from queries and videos and accordingly establishing associations between the two modalities. In contrast, this paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Dual encoding is conceptually simple, practically effective and end-to-end. As experiments on three benchmarks, i.e. MSR-VTT, TRECVID 2016 and 2017 Ad-hoc Video Search show, the proposed solution establishes a new state-of-the-art for zero-example video retrieval.

cs.CV↗

arXiv2019

Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks

The task of Language-Based Image Editing (LBIE) aims at generating a target image by editing the source image based on the given language description. The main challenge of LBIE is to disentangle the semantics in image and text and then combine them to generate realistic images. Therefore, the editing performance is heavily dependent on the learned representation. In this work, conditional generative adversarial network (cGAN) is utilized for LBIE. We find that existing conditioning methods in cGAN lack of representation power as they cannot learn the second-order correlation between two conditioning vectors. To solve this problem, we propose an improved conditional layer named Bilinear Residual Layer (BRL) to learning more powerful representations for LBIE task. Qualitative and quantitative comparisons demonstrate that our method can generate images with higher quality when compared to previous LBIE techniques.

cs.CV↗

arXiv2018

A Neural Network Aided Approach for LDPC Coded DCO-OFDM with Clipping Distortion

In this paper, a neural network-aided bit-interleaved coded modulation (NN-BICM) receiver is designed to mitigate the nonlinear clipping distortion in the LDPC coded direct currentbiased optical orthogonal frequency division multiplexing (DCOOFDM) systems. Taking the cross-entropy as loss function, a feed forward network is trained by backpropagation algorithm to output the condition probability through the softmax activation function, thereby assisting in a modified log-likelihood ratio (LLR) improvement. To reduce the complexity, this feed-forward network simplifies the input layer with a single symbol and the corresponding Gaussian variance instead of focusing on the inter-carrier interference between multiple subcarriers. On the basis of the neural network-aided BICM with Gray labelling, we propose a novel stacked network architecture of the bitinterleaved coded modulation with iterative decoding (NN-BICMID). Its performance has been improved further by calculating the condition probability with the aid of a priori probability that derived from the extrinsic LLRs in the LDPC decoder at the last iteration, at the expense of customizing neural network detectors at each iteration time separately. Utilizing the optimal DC bias as the midpoint of the dynamic region, the simulation results demonstrate that both the NN-BICM and NN-BICM-ID schemes achieve noticeable performance gains than other counterparts, in which the NN-BICM-ID clearly outperforms NN-BICM with various modulation and coding schemes.

cs.LG↗

arXiv2018

Seer: Leveraging Big Data to Navigate the Increasing Complexity of Cloud Debugging

Performance unpredictability in cloud services leads to poor user experience, degraded availability, and has revenue ramifications. Detecting performance degradation a posteriori helps the system take corrective action, but does not avoid the QoS violations. Detecting QoS violations after the fact is even more detrimental when a service consists of hundreds of thousands of loosely-coupled microservices, since performance hiccups can quickly propagate across the dependency graph of microservices. In this work we focus on anticipating QoS violations in cloud settings to mitigate performance unpredictability to begin with. We propose Seer, a cloud runtime that leverages the massive amount of tracing data cloud systems collect over time and a set of practical learning techniques to signal upcoming QoS violations, as well as identify the microservice(s) causing them. Once an imminent QoS violation is detected Seer uses machine-level hardware events to determine the cause of the QoS violation, and adjusts the resource allocations to prevent it. In local clusters with 10 40-core servers and 200-instance clusters on GCE running diverse cloud microservices, we show that Seer correctly anticipates QoS violations 91% of the time, and attributes the violation to the correct microservice in 89% of cases. Finally, Seer detects QoS violations early enough for a corrective action to almost always be applied successfully.

cs.DC↗