arXiv subjects

Wei Yang

Publications and source records attributed to Wei Yang.

At least 433 records · Page 24Linked to original sources

arXiv2019

End-to-End Open-Domain Question Answering with BERTserini

We demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

cs.CL↗

arXiv2019

Universal transfer and stacking technique of van der Waals heterostructures for spintronics

The key to achieving high-quality van der Waals heterostructure devices made from various two-dimensional (2D) materials lies in the control over clean and flexible interfaces. However, existing transfer methods based on different mediators possess insufficiencies including the presence of residues, the unavailability of flexible interface engineering, and the selectivity towards materials and substrates since their adhesions differ considerably with the various preparation conditions, from chemical vapor deposition (CVD) growth to mechanical exfoliation. In this paper, we introduce a more universal method using a prefabricated polyvinyl alcohol (PVA) film to transfer and stack 2D materials, whether they are prepared by CVD or exfoliation. This peel-off and drop-off technique promises an ideal interface of the materials without introducing contamination. In addition, the method exhibits a micron-scale spatial transfer accuracy and meets special experimental conditions such as the preparation of twisted graphene and the 2D/metal heterostructure construction. We illustrate the superiority of this method with a WSe2 vertical spin valve device, whose performance verifies the applicability and advantages of such a method for spintronics. Our PVA-assisted transfer process will promote the development of high-performance 2D-material-based devices.

physics.app-ph↗

arXiv2019

Aggregating Votes with Local Differential Privacy: Usefulness, Soundness vs. Indistinguishability

Voting plays a central role in bringing crowd wisdom to collective decision making, meanwhile data privacy has been a common ethical/legal issue in eliciting preferences from individuals. This work studies the problem of aggregating individual's voting data under the local differential privacy setting, where usefulness and soundness of the aggregated scores are of major concern. One naive approach to the problem is adding Laplace random noises, however, it makes aggregated scores extremely fragile to new types of strategic behaviors tailored to the local privacy setting: data amplification attack and view disguise attack. The data amplification attack means an attacker's manipulation power is amplified by the privacy-preserving procedure when contributing a fraud vote. The view disguise attack happens when an attacker could disguise malicious data as valid private views to manipulate the voting result. In this work, after theoretically quantifying the estimation error bound and the manipulating risk bound of the Laplace mechanism, we propose two mechanisms improving the usefulness and soundness simultaneously: the weighted sampling mechanism and the additive mechanism. The former one interprets the score vector as probabilistic data. Compared to the Laplace mechanism for Borda voting rule with $d$ candidates, it reduces the mean squared error bound by half and lowers the maximum magnitude risk bound from $+\infty$ to $O(\frac{d^3}{nε})$. The latter one randomly outputs a subset of candidates according to their total scores. Its mean squared error bound is optimized from $O(\frac{d^5}{nε^2})$ to $O(\frac{d^4}{nε^2})$, and its maximum magnitude risk bound is reduced to $O(\frac{d^2}{nε})$. Experimental results validate that our proposed approaches averagely reduce estimation error by $50\%$ and are more robust to adversarial attacks.

cs.CR↗

arXiv2019

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing defense approaches are still vulnerable to attacks, especially in a white-box attack scenario. To address this issue, we propose a new defense approach, named MulDef, based on robustness diversity. Our approach consists of (1) a general defense framework based on multiple models and (2) a technique for generating these multiple models to achieve high defense capability. In particular, given a target model, our framework includes multiple models (constructed from the target model) to form a model family. The model family is designed to achieve robustness diversity (i.e., an adversarial example successfully attacking one model cannot succeed in attacking other models in the family). At runtime, a model is randomly selected from the family to be applied on each input example. Our general framework can inspire rich future research to construct a desirable model family achieving higher robustness diversity. Our evaluation results show that MulDef (with only up to 5 models in the family) can substantially improve the target model's accuracy on adversarial examples by 22-74% in a white-box attack scenario, while maintaining similar accuracy on legitimate examples.

cs.LG↗

arXiv2019

Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search

Despite substantial interest in applications of neural networks to information retrieval, neural ranking models have only been applied to standard ad hoc retrieval tasks over web pages and newswire documents. This paper proposes MP-HCNN (Multi-Perspective Hierarchical Convolutional Neural Network) a novel neural ranking model specifically designed for ranking short social media posts. We identify document length, informal language, and heterogeneous relevance signals as features that distinguish documents in our domain, and present a model specifically designed with these characteristics in mind. Our model uses hierarchical convolutional layers to learn latent semantic soft-match relevance signals at the character, word, and phrase levels. A pooling-based similarity measurement layer integrates evidence from multiple types of matches between the query, the social media post, as well as URLs contained in the post. Extensive experiments using Twitter data from the TREC Microblog Tracks 2011--2014 show that our model significantly outperforms prior feature-based as well and existing neural ranking models. To our best knowledge, this paper presents the first substantial work tackling search over social media posts using neural ranking models.

cs.IR↗

arXiv2019

Nanoporous Aluminum-Magnesium Alloy for UV enhanced spectroscopy

We report the first preparation of nanoporous Al-Mg alloy films by selective dissolution of Mg from a Mg-rich AlxMg1-x alloy. We show how to tune the stoichiometry, the porosity and the oxide contents in the final film by modulating the starting ratio between Al and Mg and the dealloying procedure. The obtained porous metal can be exploited for enhanced UV spectroscopy. In this respect, we experimentally demonstrate its efficacy in enhancing fluorescence and surface Raman scattering for excitation wavelengths of 360 nm and 257 nm respectively. Finally, we numerically show the superior performance of the nanoporous Al-Mg alloy in the UV range when compared to equivalent porous gold structures. The large area to surface ratio provided by this material make it a promising platform for a wide range of applications in UV/deep-UV plasmonics.

physics.app-ph↗

arXiv2019

Data Augmentation for BERT Fine-Tuning in Open-Domain Question Answering

Recently, a simple combination of passage retrieval using off-the-shelf IR techniques and a BERT reader was found to be very effective for question answering directly on Wikipedia, yielding a large improvement over the previous state of the art on a standard benchmark dataset. In this paper, we present a data augmentation technique using distant supervision that exploits positive as well as negative examples. We apply a stage-wise approach to fine tuning BERT on multiple datasets, starting with data that is "furthest" from the test data and ending with the "closest". Experimental results show large gains in effectiveness over previous approaches on English QA datasets, and we establish new baselines on two recent Chinese QA datasets.

cs.CL↗

arXiv2019

Superconductors, Orbital Magnets, and Correlated States in Magic Angle Bilayer Graphene

Superconductivity often occurs close to broken-symmetry parent states and is especially common in doped magnetic insulators. When twisted close to a magic relative orientation angle near 1 degree, bilayer graphene has flat moire superlattice minibands that have emerged as a rich and highly tunable source of strong correlation physics, notably the appearance of superconductivity close to interaction-induced insulating states. Here we report on the fabrication of bilayer graphene devices with exceptionally uniform twist angles. We show that the reduction in twist angle disorder reveals insulating states at all integer occupancies of the four-fold spin/valley degenerate flat conduction and valence bands, i.e. at moire band filling factors nu = 0, +(-) 1, +(-) 2, +(-) 3, and superconductivity below critical temperatures as high as 3 K close to - 2 filling. We also observe three new superconducting domes at much lower temperatures close to the nu = 0 and nu = +(-) 1 insulating states. Interestingly, at nu = +(-) 1 we find states with non-zero Chern numbers. For nu = - 1 the insulating state exhibits a sharp hysteretic resistance enhancement when a perpendicular magnetic field above 3.6 tesla is applied, consistent with a field driven phase transition. Our study shows that symmetry-broken states, interaction driven insulators, and superconducting domes are common across the entire moire flat bands, including near charge neutrality.

cond-mat.str-el↗

arXiv2019

Simple Applications of BERT for Ad Hoc Document Retrieval

Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval. This required confronting the challenge posed by documents that are typically longer than the length of input BERT was designed to handle. We address this issue by applying inference on sentences individually, and then aggregating sentence scores to produce document scores. Experiments on TREC microblog and newswire test collections show that our approach is simple yet effective, as we report the highest average precision on these datasets by neural approaches that we are aware of.

cs.IR↗

arXiv2019

Single-spin asymmetry in dihadron production in SIDIS off the longitudinally polarized nucleon target

We study the single longitudinal-spin asymmetry of dihadron production in semi-inclusive deep inelastic scattering process. We consider the collinear picture in which the transverse momentum of the final-state hadron pair is integrated out, such that the $\sin ϕ_R$ azimuthal asymmetry arises from the coupling $h_L\, H_{1}^{\sphericalangle}$ as well as the coupling $g_1 \,\widetilde{G}^{\sphericalangle}$. We calculate the unknown twist-3 dihadron fragmentation function $\widetilde{G}^{\sphericalangle}$ using a spectator model which is successful in describing the dihadron production in the unpolarized process. Using the spectator model results for the quark distributions and dihadron fragmentation functions, we estimate the $\sin ϕ_R$ asymmetry of dihadron production in SIDIS at the kinematics of COMPASS and compare it with the COMPASS preliminary data. In addition, the prediction on the $\sin ϕ_R$ asymmetry at the typical kinematics of the future Electron Ion Collider is also presented. In order to test the reliability of the spectator model estimate, we compare the model result for the distribution $h_L$ with the Wandzura-Wilczek approximation for that distribution, and compare $H_{1}^{\sphericalangle}$ with the existing parametrization. Although the asymmetry is dominated by the $h_L H_{1}^{\sphericalangle}$ term, we find that the contribution from the $g_1\, \widetilde{G}^{\sphericalangle}$ term should also be taken into account in certain kinematical region.

hep-ph↗

arXiv2019

On the Fundamental Limits of MIMO Massive Multiple Access Channels

In this paper, we study the multiple-antenna wireless communication networks, where a large number of devices simultaneously communicate with an access point. The capacity region of multiple-input multiple-output massive multiple access channels (MIMO mMAC) is investigated. While joint typicality decoding is utilized to establish the achievability of capacity region for conventional MAC with fixed number of users, the technique is not directly applicable for MIMO mMAC. Instead, an information-theoretic approach based on Gallager's error exponent analysis is exploited to characterize the \textcolor[rgb]{0,0,0}{finite dimension region} of MIMO mMAC. Theoretical results reveal that the finite dimension region of MIMO mMAC is dominated by sum rate constraint only, and the individual user rate is determined by a specific factor that corresponds to the allocation of sum rate. The rate in conventional MAC is not achievable with massive multiple access, which is due to the fact that successive interference cancellation cannot guarantee an arbitrary small error decoding probability for MIMO mMAC. The results further imply that, asymptotically, the individual user rate is independent of the number of transmit antennas, and channel hardening makes the individual user rate close to that when only statistic knowledge of channel is available at receiver. The finite dimension region of MIMO mMAC is a generalization of the symmetric rate in Chen \emph{et al.} (2017).

cs.IT↗

arXiv2019

Raman spectrum of 1T'-WTe2 under tensile strain: A first-principles prediction

Monolayer WTe2 attracts rapidly growing interests for its large-gap quantum spin Hall effect,which enables promising apllications in flexible logic devices. Due to one-dimensional W-W chains,1T'-WTe2 exhibits unique anisotropic structure and promising properties, which can be modified by simply applying strains. Based on the first-principles simulations, we show that phonon branch undergoes soft down to negative frequency at special q points under different critical strains, i.e., epsilon_a = 11.55 percent along a-axis (with W-W chains) direction, epsilon_b = 7.0 percent along b-axis direction and epsilon_ab = 8.44 percent along biaxial direction. Before each critical strain, the Raman-shift of A1_g, A3_g, and A4_g modes, corresponding to the main peaks in Raman spectra of 1T'-WTe2 , shows anisotropic response to uniaxial strain but most sensitive to biaxial strain. Interestingly, we find that the frequency shift of A3_g mode show parabolic characters of strained 1T'-WTe2, then we split it into two parts and it shows a Raman-shift transition at about 5 percent strains. While for the A1_g and A4_g modes,the frequencies change linearly. Through careful structure and vibration analysis, we try to explain these Raman irregularity in strained 1T'-WTe2.

cond-mat.mtrl-sci↗

arXiv2019

Building Secure SRAM PUF Key Generators on Resource Constrained Devices

A securely maintained key is the premise upon which data stored and transmitted by ubiquitously deployed resource limited devices, such as those in the Internet of Things (IoT), are protected. However, many of these devices lack a secure non-volatile memory (NVM) for storing keys because of cost constraints. Silicon physical unclonable functions (PUFs) offering unique device specific secrets to electronic commodities are a low-cost alternative to secure NVM. As a physical hardware security primitive, reliability of a PUF is affected by thermal noise and changes in environmental conditions; consequently, PUF responses cannot be directly employed as cryptographic keys. A fuzzy extractor can turn noisy PUF responses into usable cryptographic keys. However, a fuzzy extractor is not immediately mountable on (highly) resource constrained devices due to its implementation overhead. We present a methodology for constructing a lightweight and secure PUF key generator for resource limited devices. In particular, we focus on PUFs constructed from pervasively embedded SRAM in modern microcontroller units and use a batteryless computational radio frequency identification (CRFID) device as a representative resource constrained IoT device in a case study.

cs.CR↗

arXiv2019

A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings

Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the effectiveness of the resulting embeddings. How to effectively train word embedding models using data from different domains remains a problem that is underexplored. In this paper, we present a simple yet effective method for learning word embeddings based on text from different domains. We demonstrate the effectiveness of our approach through extensive experiments on various down-stream NLP tasks.

cs.CL↗

arXiv2019

Attention-based Walking Gait and Direction Recognition in Wi-Fi Networks

The study of human gait recognition has been becoming an active research field. In this paper, we propose to adopt the attention-based Recurrent Neural Network (RNN) encoder-decoder framework to implement a cycle-independent human gait and walking direction recognition system in Wi-Fi networks. For capturing more human walking dynamics, two receivers together with one transmitter are deployed in different spatial layouts. In the proposed system, the Channel State Information (CSI) measurements from different receivers are first gathered together and refined to form an integrated walking profile. Then, the RNN encoder reads and encodes the walking profile into primary feature vectors. Given a specific recognition task, the decoder computes a corresponding attention vector which is a weighted sum of the primary features assigned with different attentions, and is finally used to predict the target. The attention scheme motivates our system to learn to adaptively align with different critical clips of CSI data sequence for human walking gait and direction recognitions. We implement our system on commodity Wi-Fi devices in indoor environment, and the experimental results demonstrate that our system can achieve average F1 scores of 89.69% for gait recognition from a group of 8 subjects and 95.06% for direction recognition from 8 walking directions, in addition, the average accuracies of these two recognition tasks both exceed 97%.

cs.HC↗

arXiv2018

Hierarchical Macro Strategy Model for MOBA Game AI

The next challenge of game AI lies in Real Time Strategy (RTS) games. RTS games provide partially observable gaming environments, where agents interact with one another in an action space much larger than that of GO. Mastering RTS games requires both strong macro strategies and delicate micro level execution. Recently, great progress has been made in micro level execution, while complete solutions for macro strategies are still lacking. In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games. Trained by the Hierarchical Macro Strategy model, agents explicitly make macro strategy decisions and further guide their micro level execution. Moreover, each of the agents makes independent strategy decisions, while simultaneously communicating with the allies through leveraging a novel imitated cross-agent communication mechanism. We perform comprehensive evaluations on a popular 5v5 Multiplayer Online Battle Arena (MOBA) game. Our 5-AI team achieves a 48% winning rate against human player teams which are ranked top 1% in the player ranking system.

cs.MA↗

arXiv2018

Sequenced-Replacement Sampling for Deep Learning

We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill the original dataset by successively adding samples according to their sequence index. Thus we carry out replacement sampling but in a batched and sequenced way. In a sense, SRS could be viewed as a way of performing "mini-batch augmentation". It is particularly useful for a task where we have a relatively small images-per-class such as CIFAR-100. Together with a longer period of initial large learning rate, it significantly improves the classification accuracy in CIFAR-100 over the current state-of-the-art results. Our experiments indicate that training deeper networks with SRS is less prone to over-fitting. In the best case, we achieve an error rate as low as 10.10%.

cs.LG↗

arXiv2018

Visual Semantic Navigation using Scene Priors

How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we search cabinets near the coffee machine and for fruits we try the fridge. In this work, we focus on incorporating semantic priors in the task of semantic navigation. We propose to use Graph Convolutional Networks for incorporating the prior knowledge into a deep reinforcement learning framework. The agent uses the features from the knowledge graph to predict the actions. For evaluation, we use the AI2-THOR framework. Our experiments show how semantic knowledge improves performance significantly. More importantly, we show improvement in generalization to unseen scenes and/or objects. The supplementary video can be accessed at the following link: https://youtu.be/otKjuO805dE .

cs.CV↗