arXiv subjects

Can Wang

Publications and source records attributed to Can Wang.

At least 217 records · Page 12Linked to original sources

arXiv2020

CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation

Sampling strategies have been widely applied in many recommendation systems to accelerate model learning from implicit feedback data. A typical strategy is to draw negative instances with uniform distribution, which however will severely affect model's convergency, stability, and even recommendation accuracy. A promising solution for this problem is to over-sample the ``difficult'' (a.k.a informative) instances that contribute more on training. But this will increase the risk of biasing the model and leading to non-optimal results. Moreover, existing samplers are either heuristic, which require domain knowledge and often fail to capture real ``difficult'' instances; or rely on a sampler model that suffers from low efficiency. To deal with these problems, we propose an efficient and effective collaborative sampling method CoSam, which consists of: (1) a collaborative sampler model that explicitly leverages user-item interaction information in sampling probability and exhibits good properties of normalization, adaption, interaction information awareness, and sampling efficiency; and (2) an integrated sampler-recommender framework, leveraging the sampler model in prediction to offset the bias caused by uneven sampling. Correspondingly, we derive a fast reinforced training algorithm of our framework to boost the sampler performance and sampler-recommender collaboration. Extensive experiments on four real-world datasets demonstrate the superiority of the proposed collaborative sampler model and integrated sampler-recommender framework.

cs.IR↗

arXiv2020

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable. To this end, we propose two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities: 1) a Node Adaptive Parameter Learning (NAPL) module to capture node-specific patterns; 2) a Data Adaptive Graph Generation (DAGG) module to infer the inter-dependencies among different traffic series automatically. We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks. Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.

cs.LG↗

arXiv2020

Strong Ferromagnetism Achieved via Breathing Lattices in Atomically Thin Cobaltites

Low-dimensional quantum materials that remain strongly ferromagnetic down to mono layer thickness are highly desired for spintronic applications. Although oxide materials are important candidates for next generation of spintronic, ferromagnetism decays severely when the thickness is scaled to the nano meter regime, leading to deterioration of device performance. Here we report a methodology for maintaining strong ferromagnetism in insulating LaCoO3 (LCO) layers down to the thickness of a single unit cell. We find that the magnetic and electronic states of LCO are linked intimately to the structural parameters of adjacent "breathing lattice" SrCuO2 (SCO). As the dimensionality of SCO is reduced, the lattice constant elongates over 10% along the growth direction, leading to a significant distortion of the CoO6 octahedra, and promoting a higher spin state and long-range spin ordering. For atomically thin LCO layers, we observe surprisingly large magnetic moment (0.5 uB/Co) and Curie temperature (75 K), values larger than previously reported for any mono layer oxide. Our results demonstrate a strategy for creating ultra thin ferromagnetic oxides by exploiting atomic hetero interface engineering,confinement-driven structural transformation, and spin-lattice entanglement in strongly correlated materials.

cond-mat.mtrl-sci↗

arXiv2020

Strain-mediated high conductivity in ultrathin antiferromagnetic metallic nitrides

Strain engineering provides the ability to control the ground states and associated phase transition in the epitaxial films. However, the systematic study of intrinsic characters and their strain dependency in transition-metal nitrides remains challenging due to the difficulty in fabricating the stoichiometric and high-quality films. Here we report the observation of electronic state transition in highly crystalline antiferromagnetic CrN films with strain and reduced dimensionality. Shrinking the film thickness to a critical value of ~ 30 unit cells, a profound conductivity reduction accompanied by unexpected volume expansion is observed in CrN films. The electrical conductivity is observed surprisingly when the CrN layer as thin as single unit cell thick, which is far below the critical thickness of most metallic films. We found that the metallicity of an ultrathin CrN film recovers from an insulating behavior upon the removal of as-grown strain by fabrication of first-ever freestanding nitride films. Both first-principles calculations and linear dichroism measurements reveal that the strain-mediated orbital splitting effectively customizes the relatively small bandgap at the Fermi level, leading to exotic phase transition in CrN. The ability to achieve highly conductive nitride ultrathin films by harness strain-controlling over competing phases can be used for utilizing their exceptional characteristics.

cond-mat.mtrl-sci↗

arXiv2020

TRec: Sequential Recommender Based On Latent Item Trend Information

Recommendation system plays an important role in online web applications. Sequential recommender further models user short-term preference through exploiting information from latest user-item interaction history. Most of the sequential recommendation methods neglect the importance of ever-changing item popularity. We propose the model from the intuition that items with most user interactions may be popular in the past but could go out of fashion in recent days. To this end, this paper proposes a novel sequential recommendation approach dubbed TRec, TRec learns item trend information from implicit user interaction history and incorporates item trend information into next item recommendation tasks. Then a self-attention mechanism is used to learn better node representation. Our model is trained via pairwise rank-based optimization. We conduct extensive experiments with seven baseline methods on four benchmark datasets, The empirical result shows our approach outperforms other stateof-the-art methods while maintains a superiorly low runtime cost. Our study demonstrates the importance of item trend information in recommendation system designs, and our method also possesses great efficiency which enables it to be practical in real-world scenarios.

cs.IR↗

arXiv2020

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

Remarkable progress has been made in 3D human pose estimation from a monocular RGB camera. However, only a few studies explored 3D multi-person cases. In this paper, we attempt to address the lack of a global perspective of the top-down approaches by introducing a novel form of supervision - Hierarchical Multi-person Ordinal Relations (HMOR). The HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically, which captures the body-part and joint level semantic and maintains global consistency at the same time. In our approach, an integrated top-down model is designed to leverage these ordinal relations in the learning process. The integrated model estimates human bounding boxes, human depths, and root-relative 3D poses simultaneously, with a coarse-to-fine architecture to improve the accuracy of depth estimation. The proposed method significantly outperforms state-of-the-art methods on publicly available multi-person 3D pose datasets. In addition to superior performance, our method costs lower computation complexity and fewer model parameters.

cs.CV↗

arXiv2020

Whole-Body Human Pose Estimation in the Wild

This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet. As existing datasets do not have whole-body annotations, previous methods have to assemble different deep models trained independently on different datasets of the human face, hand, and body, struggling with dataset biases and large model complexity. To fill in this blank, we introduce COCO-WholeBody which extends COCO dataset with whole-body annotations. To our best knowledge, it is the first benchmark that has manual annotations on the entire human body, including 133 dense landmarks with 68 on the face, 42 on hands and 23 on the body and feet. A single-network model, named ZoomNet, is devised to take into account the hierarchical structure of the full human body to solve the scale variation of different body parts of the same person. ZoomNet is able to significantly outperform existing methods on the proposed COCO-WholeBody dataset. Extensive experiments show that COCO-WholeBody not only can be used to train deep models from scratch for whole-body pose estimation but also can serve as a powerful pre-training dataset for many different tasks such as facial landmark detection and hand keypoint estimation. The dataset is publicly available at https://github.com/jin-s13/COCO-WholeBody.

cs.CV↗

arXiv2020

Spectrum-Guided Adversarial Disparity Learning

It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this work, we propose a novel end-to-end knowledge directed adversarial learning framework, which portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity. Furthermore, the domain knowledge is incorporated in an unsupervised manner to guide the optimization and further boosts the performance. The experiments on four HAR benchmark datasets demonstrate the robustness and generalization of our proposed methods over a set of state-of-the-art. We further prove the effectiveness of automatic domain knowledge incorporation in performance enhancement.

cs.LG↗

arXiv2020

Pose-aware Adversarial Domain Adaptation for Personalized Facial Expression Recognition

Current facial expression recognition methods fail to simultaneously cope with pose and subject variations. In this paper, we propose a novel unsupervised adversarial domain adaptation method which can alleviate both variations at the same time. Specially, our method consists of three learning strategies: adversarial domain adaptation learning, cross adversarial feature learning, and reconstruction learning. The first aims to learn pose- and expression-related feature representations in the source domain and adapt both feature distributions to that of the target domain by imposing adversarial learning. By using personalized adversarial domain adaptation, this learning strategy can alleviate subject variations and exploit information from the source domain to help learning in the target domain. The second serves to perform feature disentanglement between pose- and expression-related feature representations by impulsing pose-related feature representations expression-undistinguished and the expression-related feature representations pose-undistinguished. The last can further boost feature learning by applying face image reconstructions so that the learned expression-related feature representations are more pose- and identity-robust. Experimental results on four benchmark datasets demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2020

Cavity Quantum Electrodynamics with Second-Order Topological Corner State

Topological photonics provides a new paradigm in studying cavity quantum electrodynamics with robustness to disorder. In this work, we demonstrate the coupling between single quantum dots and the second-order topological corner state. Based on the second-order topological corner state, a topological photonic crystal cavity is designed and fabricated into GaAs slabs with quantum dots embedded. The coexistence of corner state and edge state with high quality factor close to 2000 is observed. The enhancement of photoluminescence intensity and emission rate are both observed when the quantum dot is on resonance with the corner state. This result enables the application of topology into cavity quantum electrodynamics, offering an approach to topological devices for quantum information processing.

cond-mat.mes-hall↗

arXiv2020

Low-threshold topological nanolasers based on second-order corner state

The topological lasers, which are immune to imperfections and disorders, have been recently demonstrated based on many kinds of robust edge states, being mostly at microscale. The realization of 2D on-chip topological nanolasers, having the small footprint, low threshold and high energy efficiency, is still to be explored. Here, we report on the first experimental demonstration of the topological nanolaser with high performance in 2D photonic crystal slab. Based on the generalized 2D Su-Schrieffer-Heeger model, a topological nanocavity is formed with the help of the Wannier-type 0D corner state. Laser behaviors with low threshold about 1 $μW$ and high spontaneous emission coupling factor of 0.25 are observed with quantum dots as the active material. Such performance is much better than that of topological edge lasers and comparable to conventional photonic crystal nanolasers. Our experimental demonstration of the low-threshold topological nanolaser will be of great significance to the development of topological nanophotonic circuitry for manipulation of photons in classical and quantum regimes.

physics.optics↗

arXiv2020

Defective Edge states and Anomalous Bulk-boundary Correspondence for Topological Insulators under Non-Hermitian Similarity Transformation

It was known that for non-Hermitian topological systems due to the non-Hermitian skin effect, the bulk-edge correspondence is broken down. In this paper, by using one-dimensional Su-SchriefferHeeger model and two-dimensional (deformed) Qi-Wu-Zhang model as examples, we focus on a special type of non-Hermitian topological system without non-Hermitian skin effect-topological systems under non-Hermitian similarity transformation. In these non-Hermitian systems, the defective edge states and the breakdown of bulk-edge correspondence are discovered. To characterize the topological properties, we introduce a new type of inversion symmetry-protected topological invariant-total Z2 topological invariant. In topological phases, defective edge states appear. With the help of the effective edge Hamiltonian, we find that the defective edge states are protected by (generalized) chiral symmetry and thus the (singular) defective edge states are unstable against the perturbation breaking the chiral symmetry. In addition, the results are generalized to nonHermitian topological insulators with inversion symmetry in higher dimensions. This work could help people to understand the defective edge states and the breakdown of bulk-edge correspondence for non-Hermitian topological systems.

cond-mat.mes-hall↗

arXiv2020

Effective non-Hermitian physics for degenerate ground states of a nonHermitian Ising model with $\mathcal{RT}$ symmetry

In this paper, based on a one-dimensional non-Hermitian spin model with $\mathcal{RT}$-invariant term, we study the non-Hermitian physics for the two (nearly) degenerate ground states. By using the high-order perturbation method, an effective pseudo-spin model is obtained to describe non-Hermitian physics for the two (nearly) degenerate ground states, which are precisely consistent with the numerical calculations. We found that there may exist effective (anti) $\mathcal{PT}$ symmetry for the effective pseudo-spin model of the two (nearly) degenerate ground states. In particular, there exists spontaneous (anti) $\mathcal{PT}$ -symmetry breaking for the topological degenerate ground states with tunable parameters in external fields. We also found that even a very tiny imaginary external field applied will drive $\mathcal{PT}$ phase transition.

cond-mat.stat-mech↗

arXiv2020

Fast Adaptively Weighted Matrix Factorization for Recommendation with Implicit Feedback

Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user's preference; or adaptively infer personalized confidence weights but suffer from low efficiency. To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.

cs.IR↗

arXiv2020

Identifying defect-related quantum emitters in monolayer WSe$_2$

Monolayer transition metal dichalcogenides have recently attracted great interests because the quantum dots embedded in monolayer can serve as optically active single photon emitters. Here, we provide an interpretation of the recombination mechanisms of these quantum emitters through polarization-resolved and magneto-optical spectroscopy at low temperature. Three types of defect-related quantum emitters in monolayer tungsten diselenide (WSe$_2$) are observed, with different exciton g factors of 2.02, 9.36 and unobservable Zeeman shift, respectively. The various magnetic response of the spatially localized excitons strongly indicate that the radiative recombination stems from the different transitions between defect-induced energy levels, valance and conduction bands. Furthermore, the different g factors and zero-field splittings of the three types of emitters strongly show that quantum dots embedded in monolayer have various types of confining potentials for localized excitons, resulting in electron-hole exchange interaction with a range of values in the presence of anisotropy. Our work further sheds light on the recombination mechanisms of defect-related quantum emitters and paves a way toward understanding the role of defects in single photon emitters in atomically thin semiconductors.

cond-mat.mes-hall↗

arXiv2019

Hierarchical Graph Pooling with Structure Learning

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures. HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs. More specifically, the graph pooling operation adaptively selects a subset of nodes to form an induced subgraph for the subsequent layers. To preserve the integrity of graph's topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. By combining HGP-SL operator with graph neural networks, we perform graph level representation learning with focus on graph classification task. Experimental results on six widely used benchmarks demonstrate the effectiveness of our proposed model.

cs.LG↗

arXiv2019

Online Knowledge Distillation with Diverse Peers

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate predictions of multiple student models as targets to train each student model. Although group-derived targets give a good recipe for teacher-free distillation, group members are homogenized quickly with simple aggregation functions, leading to early saturated solutions. In this work, we propose Online Knowledge Distillation with Diverse peers (OKDDip), which performs two-level distillation during training with multiple auxiliary peers and one group leader. In the first-level distillation, each auxiliary peer holds an individual set of aggregation weights generated with an attention-based mechanism to derive its own targets from predictions of other auxiliary peers. Learning from distinct target distributions helps to boost peer diversity for effectiveness of group-based distillation. The second-level distillation is performed to transfer the knowledge in the ensemble of auxiliary peers further to the group leader, i.e., the model used for inference. Experimental results show that the proposed framework consistently gives better performance than state-of-the-art approaches without sacrificing training or inference complexity, demonstrating the effectiveness of the proposed two-level distillation framework.

cs.LG↗

arXiv2019

Multiferroic metal-PbNb$_{0.12}$Ti$_{0.88}$O$_{3-δ}$ films on Nb-doped STO

Ferroelectricity-the switchable intrinsic electric polarization-has not yet been attained in a metal experimentally and is in fact generally deemed irreconcilable with free carriers, although polar metal has been achieved recently. Multiferroic metal has never even been proposed though multiferroics have been widely investigated. Here we report a room-temperature coexistence of multiferroicity and metallic behavior in PbNb0.12Ti0.88O3-delta films. The oxygen-vacancy-induced electrons become delocalized and ameliorate the ferromagnetic properties of these films, whereas they fail to vanish the polar displacements nor the individual dipole in each unit cell. This concurrent appearance of multiferroicity and metallicity is also confirmed by our first-principles calculation performed on 12.5% Nb-doped PbTiO3 with oxygen vacancies. These findings break a path to multiferroic metallic materials and offer a potential application for multiferroic spintronic devices.

physics.app-ph↗