arXiv subjects

Xiaolei Liu

Publications and source records attributed to Xiaolei Liu.

27 records · Page 2Linked to original sources

arXiv2021

HCGR: Hyperbolic Contrastive Graph Representation Learning for Session-based Recommendation

Session-based recommendation (SBR) learns users' preferences by capturing the short-term and sequential patterns from the evolution of user behaviors. Among the studies in the SBR field, graph-based approaches are a relatively powerful kind of way, which generally extract item information by message aggregation under Euclidean space. However, such methods can't effectively extract the hierarchical information contained among consecutive items in a session, which is critical to represent users' preferences. In this paper, we present a hyperbolic contrastive graph recommender (HCGR), a principled session-based recommendation framework involving Lorentz hyperbolic space to adequately capture the coherence and hierarchical representations of the items. Within this framework, we design a novel adaptive hyperbolic attention computation to aggregate the graph message of each user's preference in a session-based behavior sequence. In addition, contrastive learning is leveraged to optimize the item representation by considering the geodesic distance between positive and negative samples in hyperbolic space. Extensive experiments on four real-world datasets demonstrate that HCGR consistently outperforms state-of-the-art baselines by 0.43$\%$-28.84$\%$ in terms of $HitRate$, $NDCG$ and $MRR$.

cs.IR↗

arXiv2021

Observation of an Unusual Colossal Anisotropic Magnetoresistance Effect in an Antiferromagnetic Semiconductor

Searching for novel antiferromagnetic materials with large magnetotransport response is highly demanded for constructing future spintronic devices with high stability, fast switching speed, and high density. Here we report a colossal anisotropic magnetoresistance effect in an antiferromagnetic binary compound with layered structure rare-earth dichalcogenide EuTe2. The AMR reaches 40000%, which is 4 orders of magnitude larger than that in conventional antiferromagnetic alloys. Combined magnetization, resistivity, and theoretical analysis reveal that the colossal AMR effect is attributed to a novel mechanism of vector-field tunable band structure, rather than the conventional spin-orbit coupling mechanism. Moreover, it is revealed that the strong hybridization between orbitals of Eu-layer with localized spin and Te-layer with itinerant carriers is extremely important for the large AMR effect. Our results suggest a new direction towards exploring AFM materials with prominent magnetotransport properties, which creates an unprecedented opportunity for AFM spintronics applications.

cond-mat.mtrl-sci↗

arXiv2020

High-Pressure Crystal Growth, Superconducting Properties, and Electronic Band Structure of Nb2P5

Orthorhombic (space group: Pnma) Nb2P5 is a high-pressure phase that is quenchable to ambient pressure, which could viewed as the zigzag infinite P chain-inserted NbP2. We report herein the high-pressure crystal growth of Nb2P5 and the discovery of its superconducting transition at Tc ~ 2.6 K. The electrical resistivity, magnetization, and specific heat capacity measurements on the high-quality crystal unveiled a conventional type-II weakly coupled s-wave nature of the superconductivity, with the upper critical field Hc2(0) ~ 0.5 T, the electron-phonon coupling strength {\lambda}ep ~ 0.5 - 0.8, and the Ginzburg-Landau parameter \k{appa} ~ 100. The ab initio calculations on the electronic band structure unveiled nodal-line structures protected by different symmetries. The one caused by band inversion, for example, on the {\Gamma}-X and U-R paths of the Brillouin zone, likely could bring nontrivial topology and hence possible nontrivial surface state on the surface. The surface states on the (100), (010) and (110) surfaces were also calculated and discussed. The discovery of the phosphorus-rich Nb2P5 superconductor would be instructive for the design of more metal phosphides superconductors which might host unconventional superconductivity or potential technical applications.

cond-mat.supr-con↗

arXiv2020

The de Hass-van Alphen quantum oscillations in BaSn3 superconductor with multiple Dirac fermions

By measuring the de Hass-van Alphen effect and calculating the electronic band structure, we have investigated the bulk Fermi surface of the BaSn3 superconductor with a transition temperature of ~ 4.4 K. Striking de Haas-van Alphen (dHvA) quantum oscillations are observed when the magnetic field B is perpendicular to both (100) and (001) planes. Our analysis unveiled nontrivial Berry phase imposed in the quantum oscillations when B is perpendicular to (100), with two fundamental frequencies at 31.5 T and 306.7 T, which likely arise from two corresponding hole pockets of the bands forming a type-II Dirac point. The results are supported by the ab initio calculations indicating a type-II Dirac point setting and tilting along the high symmetric K-H line of the Brillouin zone, about 0.13 eV above the Fermi level. Moreover, the calculations also revealed other two type-I Dirac points on the high symmetric {\Gamma}-A direction, but slightly far below the Fermi level. The results demonstrate BaSn3 as an excellent platform for the study of not only exotic properties of different types of Dirac fermions in a single material, but also the interplay between nontrivial topological states and superconductivity.

cond-mat.str-el↗

arXiv2019

Robust magnetoresistance in TaAs2 under pressure up to about 37 GPa

The extremely large magnetoresistance (XMR) in nonmagnetic semimetals has inspired growing interest owing to both intriguing physics and potential applications. We report results of synchrotron X-ray diffraction (SXRD) and electrical transport measurements on TaAs2 under pressure up to ~ 37 GPa, which revealed an anisotropic compression of the unit cell, formation of unusual As-As bonds above 9.5 GPa, and enhancement of metallicity. Interestingly, the MR of TaAs2 under pressure changed gently, which at 1.7 GPa is 96.6% and at 36.6 GPa is still 36.7%. The almost robust MR under pressure could be related to the nearly stable electronic structure unveiled by the ab initio calculations. The discovery would expand the potential use of XMR even under high pressure.

cond-mat.mtrl-sci↗

arXiv2019

Quantum oscillations and nontrivial topological state in a compensated semimetal TaP2

We report systematic magneto-transport measurements and ab initio calculations on single-crystalline TaP2, a new member of the transition-metal dipnictides. We observed unsaturated magnetoresistance (MR) reaching ~ 700% at a magnetic field (B) of 9 T at 2 K along with striking Shubnikov-de Hass (SdH) oscillations. Our analysis on the SdH oscillations reveals nonzero Berry phase, indicating nontrivial band topology. The analysis also uncovers three fundamental magnetic oscillation frequencies of 72 T, 237 T, and 356 T, consistent with the theoretical calculations which reveal one hole pocket and two electron pockets at the L point and one electron pocket at the Z point of the Brillouin zone. We also found negative longitudinal MR (n-MR) within a narrow window of the angles between B and the electric current (I). The n-MR could be fitted with the Adler-Bell-Jackiw chiral anomaly equation but the origin remains yet ambiguous. The ab inito calculations suggest TaP2 as a weak topological insulator with the Z2 indices of (0; 111), which exhibits topological surface states on the (001) surface.

cond-mat.str-el↗

arXiv2019

Adversarial Samples on Android Malware Detection Systems for IoT Systems

Many IoT(Internet of Things) systems run Android systems or Android-like systems. With the continuous development of machine learning algorithms, the learning-based Android malware detection system for IoT devices has gradually increased. However, these learning-based detection models are often vulnerable to adversarial samples. An automated testing framework is needed to help these learning-based malware detection systems for IoT devices perform security analysis. The current methods of generating adversarial samples mostly require training parameters of models and most of the methods are aimed at image data. To solve this problem, we propose a \textbf{t}esting framework for \textbf{l}earning-based \textbf{A}ndroid \textbf{m}alware \textbf{d}etection systems(TLAMD) for IoT Devices. The key challenge is how to construct a suitable fitness function to generate an effective adversarial sample without affecting the features of the application. By introducing genetic algorithms and some technical improvements, our test framework can generate adversarial samples for the IoT Android Application with a success rate of nearly 100\% and can perform black-box testing on the system.

cs.CR↗

arXiv2019

A Black-box Attack on Neural Networks Based on Swarm Evolutionary Algorithm

Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of the generation approaches either assume that the attacker has full knowledge of the neural network model or are limited by the type of attacked model. In this paper, we propose a new approach that generates a black-box attack to neural networks based on the swarm evolutionary algorithm. Benefiting from the improvements in the technology and theoretical characteristics of evolutionary algorithms, our approach has the advantages of effectiveness, black-box attack, generality, and randomness. Our experimental results show that both the MNIST images and the CIFAR-10 images can be perturbed to successful generate a black-box attack with 100\% probability on average. In addition, the proposed attack, which is successful on distilled neural networks with almost 100\% probability, is resistant to defensive distillation. The experimental results also indicate that the robustness of the artificial intelligence algorithm is related to the complexity of the model and the data set. In addition, we find that the adversarial samples to some extent reproduce the characteristics of the sample data learned by the neural network model.

cs.LG↗

arXiv2019

Weighted-Sampling Audio Adversarial Example Attack

Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent potential attacks. Despite many research on this, the efficiency and the robustness of existing works are not yet satisfactory. In this paper, we propose~\textit{weighted-sampling audio adversarial examples}, focusing on the numbers and the weights of distortion to reinforce the attack. Further, we apply a denoising method in the loss function to make the adversarial attack more imperceptible. Experiments show that our method is the first in the field to generate audio adversarial examples with low noise and high audio robustness at the minute time-consuming level.

eess.AS↗