arXiv subjects

Xing Fan

Publications and source records attributed to Xing Fan.

At least 55 records · Page 3Linked to original sources

arXiv2021

ALMA: Alternating Minimization Algorithm for Clustering Mixture Multilayer Network

The paper considers a Mixture Multilayer Stochastic Block Model (MMLSBM), where layers can be partitioned into groups of similar networks, and networks in each group are equipped with a distinct Stochastic Block Model. The goal is to partition the multilayer network into clusters of similar layers, and to identify communities in those layers. Jing et al. (2020) introduced the MMLSBM and developed a clustering methodology, TWIST, based on regularized tensor decomposition. The present paper proposes a different technique, an alternating minimization algorithm (ALMA), that aims at simultaneous recovery of the layer partition, together with estimation of the matrices of connection probabilities of the distinct layers. Compared to TWIST, ALMA achieves higher accuracy both theoretically and numerically.

stat.ML↗

arXiv2021

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have been proposed to address this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with weak supervision data. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model, i.e., BART, on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.

cs.CL↗

arXiv2021

1550 nm compatible ultrafast photoconductive material based on a GaAs/ErAs/GaAs heterostructure

The sub-bandgap absorption and ultrafast relaxation in a GaAs/ErAs/GaAs heterostructure are reported. The infrared absorption and 1550 nm-excited ultrafast photo-response are studied by Fourier transform infrared (FTIR) spectrometry and time-domain pump-probe technique. The two absorption peaks located at 2.0 um (0.62 eV) and 2.7 um (0.45 eV) are originated from the ErAs/GaAs interfacial Schottky states and sub-bandgap transition within GaAs, respectively. The photo-induced carrier lifetime, excited using 1550 nm light, is measured to be as low as 190 fs for the GaAs/ErAs/GaAs heterostructure, making it a promising material for 1550-nm-technology-compatible, high critical-breakdown-field THz devices. The relaxation mechanism is proposed and the functionality of ErAs is revealed.

cond-mat.mtrl-sci↗

arXiv2021

Driven One-Particle Quantum Cyclotron

A quantum cyclotron is one trapped electron or positron that occupies only its lowest cyclotron and spin states. A master equation is solved for a driven quantum cyclotron with a QND (quantum nondemolition) coupling to a detection oscillator in thermal equilibrium - the first quantum calculation for this coupled and open system. The predicted rate of cyclotron and spin quantum jumps as a function of drive frequency, for a small coupling between the detection motion and its thermal reservoir, differs sharply from what has been predicted and used for past measurements. The calculation suggests a ten times more precise electron magnetic moment measurement is possible, as needed to investigate current differences between the most precise prediction of the standard model of particle physics, and the most accurate measurement of a property of an elementary particle.

physics.atom-ph↗

arXiv2020

Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems

Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard and costly to be collected. Therefore, We propose an augmentation framework that learns patterns from existing training pairs and generates rewrite candidates from rewrite labels inversely to compensate for insufficient QR training data. The proposed framework casts the augmentation problem as a sequence-to-sequence generation task and enforces the optimization process with a policy gradient technique for controllable rewarding. This approach goes beyond the traditional heuristics or rule-based augmentation methods and is not constrained to generate predefined patterns of swapping/replacing words. Our experimental results show its effectiveness compared with a fully trained QR baseline and demonstrate its potential application in boosting the QR performance on low-resource domains or locales.

cs.CL↗

arXiv2020

Circumventing Detector Backaction on a Quantum Cyclotron

Detector backaction can be completely evaded when the state of a one-electron quantum cyclotron is detected, but it nonetheless significantly broadens the quantum-jump resonance lineshapes from which the cyclotron frequency can be deduced. This limits the accuracy with which the electron magnetic moment can be determined to test the standard model's most precise prediction. A steady state solution to a master equation, the first quantum calculation for the open quantum cyclotron system, illustrates a method to circumvent the detection backaction upon the measured frequency.

physics.atom-ph↗

arXiv2020

Modern cities emerge as 'super-cells' where enclosed industrial systems are hotspots of goods and services

Prevailing hypotheses recognize cities as 'super-organisms' which both provides organizing principles for cities and fills the scalar gap in the hierarchical living system between ecosystems and the entire planet. However, most analogies between the traits of organisms and cities are inappropriate making the super-organism model impractical as a means to acquire new knowledge. Using a cluster analysis of 15 traits of cities and other living systems, we found that modern cities are more similar to eukaryotic cells than to multicellular organisms. Enclosed industrial systems, such as factories and greenhouses, dominate modern cities and are analogous to organelles as hotspots that provide high-flux goods and services. Therefore, we propose a 'super-cell city model' as more appropriate than the super-organism model. In addition to the theoretical significance, our model also recognizes enclosed industrial systems as functional components that improve the vitality and sustainability of cities.

physics.soc-ph↗

arXiv2020

Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification

Due to its potential wide applications in video surveillance and other computer vision tasks like tracking, person re-identification (ReID) has become popular and been widely investigated. However, conventional person re-identification can only handle RGB color images, which will fail at dark conditions. Thus RGB-infrared ReID (also known as Infrared-Visible ReID or Visible-Thermal ReID) is proposed. Apart from appearance discrepancy in traditional ReID caused by illumination, pose variations and viewpoint changes, modality discrepancy produced by cameras of the different spectrum also exists, which makes RGB-infrared ReID more difficult. To address this problem, we focus on extracting the shared cross-spectrum features of different modalities. In this paper, a novel multi-spectrum image generation method is proposed and the generated samples are utilized to help the network to find discriminative information for re-identifying the same person across modalities. Another challenge of RGB-infrared ReID is that the intra-person (images from the same person) discrepancy is often larger than the inter-person (images from different persons) discrepancy, so a dual-subspace pairing strategy is proposed to alleviate this problem. Combining those two parts together, we also design a one-stream neural network combining the aforementioned methods to extract compact representations of person images, called Cross-spectrum Dual-subspace Pairing (CDP) model. Furthermore, during the training process, we also propose a Dynamic Hard Spectrum Mining method to automatically mine more hard samples from hard spectrum based on the current model state to further boost the performance. Extensive experimental results on two public datasets, SYSU-MM01 with RGB + near-infrared images and RegDB with RGB + far-infrared images, have demonstrated the efficiency and generality of our proposed method.

cs.CV↗

arXiv2020

Pre-Training for Query Rewriting in A Spoken Language Understanding System

Query rewriting (QR) is an increasingly important technique to reduce customer friction caused by errors in a spoken language understanding pipeline, where the errors originate from various sources such as speech recognition errors, language understanding errors or entity resolution errors. In this work, we first propose a neural-retrieval based approach for query rewriting. Then, inspired by the wide success of pre-trained contextual language embeddings, and also as a way to compensate for insufficient QR training data, we propose a language-modeling (LM) based approach to pre-train query embeddings on historical user conversation data with a voice assistant. In addition, we propose to use the NLU hypotheses generated by the language understanding system to augment the pre-training. Our experiments show pre-training provides rich prior information and help the QR task achieve strong performance. We also show joint pre-training with NLU hypotheses has further benefit. Finally, after pre-training, we find a small set of rewrite pairs is enough to fine-tune the QR model to outperform a strong baseline by full training on all QR training data.

cs.CL↗

arXiv2020

Knowledge Distillation from Internal Representations

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as soft-labels to optimize the student. However, when the teacher is considerably large, there is no guarantee that the internal knowledge of the teacher will be transferred into the student; even if the student closely matches the soft-labels, its internal representations may be considerably different. This internal mismatch can undermine the generalization capabilities originally intended to be transferred from the teacher to the student. In this paper, we propose to distill the internal representations of a large model such as BERT into a simplified version of it. We formulate two ways to distill such representations and various algorithms to conduct the distillation. We experiment with datasets from the GLUE benchmark and consistently show that adding knowledge distillation from internal representations is a more powerful method than only using soft-label distillation.

cs.CL↗

arXiv2020

STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

Partial person re-identification (ReID) is a challenging task because only partial information of person images is available for matching target persons. Few studies, especially on deep learning, have focused on matching partial person images with holistic person images. This study presents a novel deep partial ReID framework based on pairwise spatial transformer networks (STNReID), which can be trained on existing holistic person datasets. STNReID includes a spatial transformer network (STN) module and a ReID module. The STN module samples an affined image (a semantically corresponding patch) from the holistic image to match the partial image. The ReID module extracts the features of the holistic, partial, and affined images. Competition (or confrontation) is observed between the STN module and the ReID module, and two-stage training is applied to acquire a strong STNReID for partial ReID. Experimental results show that our STNReID obtains 66.7% and 54.6% rank-1 accuracies on partial ReID and partial iLIDS datasets, respectively. These values are at par with those obtained with state-of-the-art methods.

cs.CV↗

arXiv2019

End-to-end Anchored Speech Recognition

Voice-controlled house-hold devices, like Amazon Echo or Google Home, face the problem of performing speech recognition of device-directed speech in the presence of interfering background speech, i.e., background noise and interfering speech from another person or media device in proximity need to be ignored. We propose two end-to-end models to tackle this problem with information extracted from the "anchored segment". The anchored segment refers to the wake-up word part of an audio stream, which contains valuable speaker information that can be used to suppress interfering speech and background noise. The first method is called "Multi-source Attention" where the attention mechanism takes both the speaker information and decoder state into consideration. The second method directly learns a frame-level mask on top of the encoder output. We also explore a multi-task learning setup where we use the ground truth of the mask to guide the learner. Given that audio data with interfering speech is rare in our training data set, we also propose a way to synthesize "noisy" speech from "clean" speech to mitigate the mismatch between training and test data. Our proposed methods show up to 15% relative reduction in WER for Amazon Alexa live data with interfering background speech without significantly degrading on clean speech.

cs.CL↗

arXiv2018

SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress. However, persons are often occluded by obstacles or other persons in practical scenarios, which makes partial person re-identification non-trivial. In this paper, we propose a spatial-channel parallelism network (SCPNet) in which each channel in the ReID feature pays attention to a given spatial part of the body. The spatial-channel corresponding relationship supervises the network to learn discriminative feature for both holistic and partial person re-identification. The single model trained on four holistic ReID datasets achieves competitive accuracy on these four datasets, as well as outperforms the state-of-the-art methods on two partial ReID datasets without training.

cs.CV↗

arXiv2018

SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification

Many current successful Person Re-Identification(ReID) methods train a model with the softmax loss function to classify images of different persons and obtain the feature vectors at the same time. However, the underlying feature embedding space is ignored. In this paper, we use a modified softmax function, termed Sphere Softmax, to solve the classification problem and learn a hypersphere manifold embedding simultaneously. A balanced sampling strategy is also introduced. Finally, we propose a convolutional neural network called SphereReID adopting Sphere Softmax and training a single model end-to-end with a new warming-up learning rate schedule on four challenging datasets including Market-1501, DukeMTMC-reID, CHHK-03, and CUHK-SYSU. Experimental results demonstrate that this single model outperforms the state-of-the-art methods on all four datasets without fine-tuning or re-ranking. For example, it achieves 94.4% rank-1 accuracy on Market-1501 and 83.9% rank-1 accuracy on DukeMTMC-reID. The code and trained weights of our model will be released.

cs.CV↗

arXiv2018

Vacuum Magnetic Birefringence Experiment as a probe of Dark Sector

Vacuum magnetic birefringence (VMB) is a nonlinear electromagnetic effect predicted by QED. In addition to the effect from QED, the effect also has a possibility to probe the dark sector. The effect predicted by QED is parity conservative, but the effect from the dark sector can induce parity violation. To pursue this possibility, we calculated the effect from the dark sector with the generalized Heisenberg-Euler effective Lagrangian that is applicable to parity-violating theories. Various dark sector models exist, among which the contribution of the dark sector neutrinos to the VMB experiment is examined. The contribution comes from the mixing of photon with the dark sector Z boson and violates parity, thus inducing a parity-violating electromagnetic interaction. If the polarization vector is denoted by $ε(θ_i)$ when its direction is rotated by an angle $θ_i$ from the direction of the applied magnetic field, the change of the polarization from $ε(45^\circ)$ to $ε(-45^\circ)$ and vice versa are examined. The contribution from the dark sector modifies the magnitude of the polarization change, so it can be detected by measuring the magnitude precisely. In addition to the change in the magnitude, the dark sector also induces parity-violating effects. We also propose a new scheme to measure the effect of parity violation directly. By measuring the change of polarization from $ε(0^{\circ})$ to $ε(90^\circ)$, and vice versa, with a ring Fabry-Pérot resonator, one can search for the effect directly. The signal that appears in this scheme is evidence of parity violation from beyond standard model theories.

hep-ph↗

arXiv2018

AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly from local feature learning, which performs an alignment/matching by calculating the shortest path between two sets of local features, without requiring extra supervision. After the joint learning, we only keep the global feature to compute the similarities between images. Our method achieves rank-1 accuracy of 94.4% on Market1501 and 97.8% on CUHK03, outperforming state-of-the-art methods by a large margin. We also evaluate human-level performance and demonstrate that our method is the first to surpass human-level performance on Market1501 and CUHK03, two widely used Person ReID datasets.

cs.CV↗

arXiv2017

Generalized Heisenberg-Euler formula in Abelian gauge theory with parity violation

A generalized Heisenberg-Euler formula is given for an Abelian gauge theory having vector as well as axial vector couplings to a massive fermion. So, the formula is applicable to a parity-violating theory. The gauge group is chosen to be $U(1)$. The formula is quite similar to that in quantum electrodynamics, but there is a complexity in which one factor (related to spin) is expressed in terms of the expectation value. The expectation value is evaluated by the contraction with the one-dimensional propagator in a given background field. The formula affords a basis to the vacuum magnetic birefringence experiment, which aims to probe the dark sector, where the interactions of the light fermions with the gauge fields are not necessarily parity conserving.

hep-ph↗

arXiv2017

New strategy for black phosphorus crystal growth through ternary clathrate

We are reporting a new synthetic strategy to grow large size black phosphorus (Black-P) crystals through a ternary clathrate Sn$_{24}$P$_{22-x}$I$_8$, under lower synthetic temperature and pressure. The Black-P crystals are found grown in situ at the site where the solid clathrate originally resides, which suggests chemical vapor mineralizer does not play a critical role for the Black-P formation. More detailed systematical studies has indicated the P vacancies in the framework of ternary clathrate Sn$_{24}$P$_{22-x}$I$_8$ is important for the subsequent Black-P from phosphorus vapors, and a likely Vapor-Solid-Solid (VSS) model is responsible for the Black-P crystal growth. The obtained room temperature mobility μ is ~ 350 $cm^2/Vs$ from Hall measurements at mechanically-cleaved flake, where noticeable micro-cracks are visible. The obtained high mobility value further suggest the high quality of the Black-P crystals synthesized through this route.

cond-mat.mtrl-sci↗