arXiv subjects

Jian Xiong

Publications and source records attributed to Jian Xiong.

25 records · Page 2Linked to original sources

arXiv2020

Multi-View Spectral Clustering with High-Order Optimal Neighborhood Laplacian Matrix

Multi-view spectral clustering can effectively reveal the intrinsic cluster structure among data by performing clustering on the learned optimal embedding across views. Though demonstrating promising performance in various applications, most of existing methods usually linearly combine a group of pre-specified first-order Laplacian matrices to construct the optimal Laplacian matrix, which may result in limited representation capability and insufficient information exploitation. Also, storing and implementing complex operations on the $n\times n$ Laplacian matrices incurs intensive storage and computation complexity. To address these issues, this paper first proposes a multi-view spectral clustering algorithm that learns a high-order optimal neighborhood Laplacian matrix, and then extends it to the late fusion version for accurate and efficient multi-view clustering. Specifically, our proposed algorithm generates the optimal Laplacian matrix by searching the neighborhood of the linear combination of both the first-order and high-order base Laplacian matrices simultaneously. By this way, the representative capacity of the learned optimal Laplacian matrix is enhanced, which is helpful to better utilize the hidden high-order connection information among data, leading to improved clustering performance. We design an efficient algorithm with proved convergence to solve the resultant optimization problem. Extensive experimental results on nine datasets demonstrate the superiority of our algorithm against state-of-the-art methods, which verifies the effectiveness and advantages of the proposed algorithm.

cs.LG↗

arXiv2020

Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation

Session-based recommender systems have attracted much attention recently. To capture the sequential dependencies, existing methods resort either to data augmentation techniques or left-to-right style autoregressive training.Since these methods are aimed to model the sequential nature of user behaviors, they ignore the future data of a target interaction when constructing the prediction model for it. However, we argue that the future interactions after a target interaction, which are also available during training, provide valuable signal on user preference and can be used to enhance the recommendation quality. Properly integrating future data into model training, however, is non-trivial to achieve, since it disobeys machine learning principles and can easily cause data leakage. To this end, we propose a new encoder-decoder framework named Gap-filling based Recommender (GRec), which trains the encoder and decoder by a gap-filling mechanism. Specifically, the encoder takes a partially-complete session sequence (where some items are masked by purpose) as input, and the decoder predicts these masked items conditioned on the encoded representation. We instantiate the general GRec framework using convolutional neural network with sparse kernels, giving consideration to both accuracy and efficiency. We conduct experiments on two real-world datasets covering short-, medium-, and long-range user sessions, showing that GRec significantly outperforms the state-of-the-art sequential recommendation methods. More empirical studies verify the high utility of modeling future contexts under our GRec framework.

cs.IR↗

arXiv2019

Phonon and Photon Lasing Dynamics in Optomechanical Cavities

Lasers differ from other light sources in that they are coherent, and their coherence makes them indispensable to both fundamental research and practical application. In optomechanical cavities, phonon and photon lasing is facilitated by the ability of photons and phonons to interact intensively and excite one another coherently. The lasing linewidths of both phonons and photons are critical for practical application. However, thus far, these linewidths have not been explored in detail in cavity optomechanical systems. This study investigates the underlying dynamics of lasing in optomechanical cavities and experimentally demonstrates simultaneous photon and phonon lasing with narrow linewidths in a silicon optomechanical crystal cavity. We find that the linewidths can be accounted for by two distinct physical mechanisms in two regimes, namely the normal regime and the reversed regime, where the intrinsic optical decay rate is either larger or smaller than the intrinsic mechanical decay rate. In the normal regime, an ultra-narrow spectral linewidth of 5.4 kHz for phonon lasing at 6.22 GHz can be achieved regardless of the linewidth of the pump light, while these results are counterintuitively unattainable for photon lasing in the reversed regime. These results pave the way towards harnessing the coherence of both photons and phonons in silicon photonic devices and reshaping their spectra, potentially opening up new technologies in sensing, metrology, spectroscopy, and signal processing, as well as in applications requiring sources that offer an ultra-high degree of coherence.

physics.optics↗

arXiv2019

Phonon-laser sensing in a hetero optomechanical crystal cavity

Micro- and nanomechanical resonators have emerged as promising platforms for sensing a broad range of physical properties such as mass, force, torque, magnetic field, and acceleration. The sensing performance relies critically on the motional mass, the mechanical frequency, and the linewidth of the mechanical resonator. Here, we demonstrate a hetero optomechanical crystal (OMC) cavity based on a silicon nanobeam structure. The cavity supports phonon lasing in a fundamental mechanical mode with a frequency of 5.91 GHz, an effective mass of 116 fg, and a mechanical linewidth narrowing from 3.3 MHz to 5.2 kHz, while the optomechanical coupling rate of is as high as 1.9 MHz. With this phonon laser, the on-chip sensing with a resolution of $δ$$λ$/$λ$ = 1.0*10-8 can be attained, which is at least two orders of magnitude larger than that obtained with conventional silicon-based sensors. The use of a silicon-based hetero OMC cavity that harnesses phonon lasing could pave the way towards exciting, high-precision sensors that lend themselves to silicon monolithic integration and offer unprecedented sensitivity for broad physical sensing applications.

physics.optics↗

arXiv2019

Learning Cross-Domain Representation with Multi-Graph Neural Network

Learning effective embedding has been proved to be useful in many real-world problems, such as recommender systems, search ranking and online advertisement. However, one of the challenges is data sparsity in learning large-scale item embedding, as users' historical behavior data are usually lacking or insufficient in an individual domain. In fact, user's behaviors from different domains regarding the same items are usually relevant. Therefore, we can learn complete user behaviors to alleviate the sparsity using complementary information from correlated domains. It is intuitive to model users' behaviors using graph, and graph neural networks (GNNs) have recently shown the great power for representation learning, which can be used to learn item embedding. However, it is challenging to transfer the information across domains and learn cross-domain representation using the existing GNNs. To address these challenges, in this paper, we propose a novel model - Deep Multi-Graph Embedding (DMGE) to learn cross-domain representation. Specifically, we first construct a multi-graph based on users' behaviors from different domains, and then propose a multi-graph neural network to learn cross-domain representation in an unsupervised manner. Particularly, we present a multiple-gradient descent optimizer for efficiently training the model. We evaluate our approach on various large-scale real-world datasets, and the experimental results show that DMGE outperforms other state-of-art embedding methods in various tasks.

cs.LG↗

arXiv2019

LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem,namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation.More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters,and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset.

cs.CV↗

arXiv2018

Microplasticity and yielding in crystals with heterogeneous dislocation distribution

In this study, we use discrete dislocation dynamics (DDD) simulation to investigate the effect of heterogeneous dislocation density on the transition between quasi-elastic deformation and plastic flow in face-centered cubic single crystals. By analyzing the stress-strain curves of samples with an initial, axial dislocation density gradient, we arrive at the following conclusions: (i) in the regime of quasi-elastic deformation before the onset of plastic flow, the effective elastic modulus of the simulated samples falls significantly below the value for a dislocation-free crystal. This modulus reduction increases with decreasing dislocation density gradient: crystals with homogeneous dislocation distribution are thus weakest in the quasi-elastic regime; (ii) the transition towards plastic flow occurs first in regions of reduced dislocation density. Therefore, the overall yield stress decreases with increasing dislocation density gradient; (iii) crystals with dislocation density gradient exhibit a more pronounced hardening stage during which stress is re-distributed onto stronger regions with higher dislocation density until the sample flows at a constant flow stress that is approximately independent on dislocation density gradient. We interpret these findings in terms of a continuum dislocation dynamics inspired model of dislocation density evolution that accounts for inversive dislocation motions. The transition between quasi-elastic and plastic deformation is interpreted as a transition from inversive to non-inversive dislocation motion, and the initial differences in elastic modulus are related to a density dependent polarizability of the dislocation system. The subsequent plastic flow behavior is analyzed in terms of a modified version of Mughrabi's composite model.

cond-mat.mtrl-sci↗