arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 865 records · Page 48Linked to original sources

arXiv2022

Photoionization detection of a single Er$^{3+}$ ion with sub-100-ns time resolution

Efficient detection of single optical centers in solids is essential for quantum information processing, sensing, and single-photon generation applications. In this work, we use radio-frequency (RF) reflectometry to electrically detect the photoionization induced by a single Er$^{3+}$ ion in Si. The high bandwidth and sensitivity of the RF reflectometry provide sub-100-ns time resolution for the photoionization detection. With this technique, the optically excited state lifetime of a single Er$^{3+}$ ion in a Si nano-transistor is measured for the first time to be 0.49 $\pm$ 0.04 $μ$s. Our results demonstrate an efficient approach for detecting a charge state change induced by Er excitation and relaxation. This approach could be used for fast readout of other single optical centers in solids and is attractive for large-scale integrated optical quantum systems thanks to the multi-channel RF reflectometry demonstrated with frequency multiplexing techniques.

quant-ph↗

arXiv2022

Post-Training Quantization for Cross-Platform Learned Image Compression

It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the non-deterministic calculation, which makes the probability prediction cross-platform inconsistent and frustrates successful decoding. We propose to solve this problem by introducing well-developed post-training quantization and making the model inference integer-arithmetic-only, which is much simpler than presently existing training and fine-tuning based approaches yet still keeps the superior rate-distortion performance of learned image compression. Based on that, we further improve the discretization of the entropy parameters and extend the deterministic inference to fit Gaussian mixture models. With our proposed methods, the current state-of-the-art image compression models can infer in a cross-platform consistent manner, which makes the further development and practice of learned image compression more promising.

eess.IV↗

arXiv2022

Efficient Adversarial Training with Robust Early-Bird Tickets

Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs). However, this approach is typically more expensive than traditional fine-tuning because of the necessity to generate adversarial examples via gradient descent. Delving into the optimization process of adversarial training, we find that robust connectivity patterns emerge in the early training phase (typically $0.15\sim0.3$ epochs), far before parameters converge. Inspired by this finding, we dig out robust early-bird tickets (i.e., subnetworks) to develop an efficient adversarial training method: (1) searching for robust tickets with structured sparsity in the early stage; (2) fine-tuning robust tickets in the remaining time. To extract the robust tickets as early as possible, we design a ticket convergence metric to automatically terminate the searching process. Experiments show that the proposed efficient adversarial training method can achieve up to $7\times \sim 13 \times$ training speedups while maintaining comparable or even better robustness compared to the most competitive state-of-the-art adversarial training methods.

cs.CL↗

arXiv2022

Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing

For time-critical IoT applications using deep learning, inference acceleration through distributed computing is a promising approach to meet a stringent deadline. In this paper, we implement a working prototype of a new distributed inference acceleration method HALP using three raspberry Pi 4. HALP accelerates inference by designing a seamless collaboration among edge devices (EDs) in Edge Computing. We maximize the parallelization between communication and computation among the collaborative EDs by optimizing the task partitioning ratio based on the segment-based partitioning. Experimental results show that the distributed inference HALP achieves 1.7x inference acceleration for VGG-16. Then, we combine distributed inference with conventional neural network model compression by setting up different shrinking hyperparameters for MobileNet-V1. In this way, we can further accelerate inference but at the cost of inference accuracy loss. To strike a balance between latency and accuracy, we propose dynamic model selection to select a model which provides the highest accuracy within the latency constraint. It is shown that the model selection with distributed inference HALP can significantly improve service reliability compared to the conventional stand-alone computation.

cs.CV↗

arXiv2022

Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications

This paper aims to design robust Edge Intelligence using semantic communication for time-critical IoT applications. We systematically analyze the effect of image DCT coefficients on inference accuracy and propose the channel-agnostic effectiveness encoding for offloading by transmitting the most meaningful task data first. This scheme can well utilize all available communication resource and strike a balance between transmission latency and inference accuracy. Then, we design an effectiveness decoding by implementing a novel image augmentation process for convolutional neural network (CNN) training, through which an original CNN model is transformed into a Robust CNN model. We use the proposed training method to generate Robust MobileNet-v2 and Robust ResNet-50. The proposed Edge Intelligence framework consists of the proposed effectiveness encoding and effectiveness decoding. The experimental results show that the effectiveness decoding using the Robust CNN models perform consistently better under various image distortions caused by channel errors or limited communication resource. The proposed Edge Intelligence framework using semantic communication significantly outperforms the conventional approach under latency and data rate constraints, in particular, under ultra stringent deadlines and low data rate.

cs.CV↗

arXiv2022

Template-free Prompt Tuning for Few-shot NER

Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would be time-consuming to enumerate the template queries over all potential entity spans. In this work, we propose a more elegant method to reformulate NER tasks as LM problems without any templates. Specifically, we discard the template construction process while maintaining the word prediction paradigm of pre-training models to predict a class-related pivot word (or label word) at the entity position. Meanwhile, we also explore principled ways to automatically search for appropriate label words that the pre-trained models can easily adapt to. While avoiding complicated template-based process, the proposed LM objective also reduces the gap between different objectives used in pre-training and fine-tuning, thus it can better benefit the few-shot performance. Experimental results demonstrate the effectiveness of the proposed method over bert-tagger and template-based method under few-shot setting. Moreover, the decoding speed of the proposed method is up to 1930.12 times faster than the template-based method.

cs.CL↗

arXiv2022

DINER: Disorder-Invariant Implicit Neural Representation

Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems. However, the capacity of INR is limited by the spectral bias in the network training. In this paper, we find that such a frequency-related problem could be largely solved by re-arranging the coordinates of the input signal, for which we propose the disorder-invariant implicit neural representation (DINER) by augmenting a hash-table to a traditional INR backbone. Given discrete signals sharing the same histogram of attributes and different arrangement orders, the hash-table could project the coordinates into the same distribution for which the mapped signal can be better modeled using the subsequent INR network, leading to significantly alleviated spectral bias. Experiments not only reveal the generalization of the DINER for different INR backbones (MLP vs. SIREN) and various tasks (image/video representation, phase retrieval, and refractive index recovery) but also show the superiority over the state-of-the-art algorithms both in quality and speed.

eess.IV↗

arXiv2022

Dynamical criticality of spin-shear coupling in van der Waals antiferromagnets

The interplay between a multitude of electronic, spin, and lattice degrees of freedom underlies the complex phase diagrams of quantum materials. Layer stacking in van der Waals (vdW) heterostructures is responsible for exotic electronic and magnetic properties, which inspires stacking control of two-dimensional magnetism. Beyond the interplay between stacking order and interlayer magnetism, we discover a spin-shear coupling mechanism in which a subtle shear of the atomic layers can have a profound effect on the intralayer magnetic order in a family of vdW antiferromagnets. Using time-resolved x-ray diffraction and optical linear dichroism measurements, interlayer shear is identified as the primary structural degree of freedom that couples with magnetic order. The recovery times of both shear and magnetic order upon optical excitation diverge at the magnetic ordering temperature with the same critical exponent. The time-dependent Ginzburg-Landau theory shows that this concurrent critical slowing down arises from a linear coupling of the interlayer shear to the magnetic order, which is dictated by the broken mirror symmetry intrinsic to the monoclinic stacking. Our results highlight the importance of interlayer shear in ultrafast control of magnetic order via spin-mechanical coupling.

cond-mat.mtrl-sci↗

arXiv2022

Robust Lottery Tickets for Pre-trained Language Models

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models. However, these tickets are proved to be notrobust to adversarial examples, and even worse than their PLM counterparts. To address this problem, we propose a novel method based on learning binary weight masks to identify robust tickets hidden in the original PLMs. Since the loss is not differentiable for the binary mask, we assign the hard concrete distribution to the masks and encourage their sparsity using a smoothing approximation of L0 regularization.Furthermore, we design an adversarial loss objective to guide the search for robust tickets and ensure that the tickets perform well bothin accuracy and robustness. Experimental results show the significant improvement of the proposed method over previous work on adversarial robustness evaluation.

cs.CL↗

arXiv2022

Discovery of charge order and corresponding edge state in kagome magnet FeGe

Kagome materials often host exotic quantum phases, including spin liquids, Chern gap, charge order, and superconductivity. Existing scanning microscopy studies of the kagome charge order have been limited to non-kagome surface layers. Here we tunnel into the kagome lattice of FeGe to uncover features of the charge order. Our spectroscopic imaging identifes a 2x2 charge order in the magnetic kagome lattice, resembling that discovered in kagome superconductors. Spin-mapping across steps of unit-cell-height demonstrates that this charge order emerges from spin-polarized electrons with an antiferromagnetic stacking order. We further uncover the correlation between antiferromagnetism and charge order anisotropy, highlighting the unusual magnetic coupling of the charge order. Finally, we detect a pronounced edge state within the charge order energy gap, which is robust against the irregular shape of the kagome lattice edges. We discuss our results with the theoretically considered topological features of the kagome charge order including orbital magnetism and bulk-boundary correspondence.

cond-mat.str-el↗

arXiv2022

Neural Parameterization for Dynamic Human Head Editing

Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene. These representations, however, suffer from poor editability. On the other hand, explicit representations such as polygonal meshes allow easy editing but are not as suitable for reconstructing accurate details in dynamic human heads, such as fine facial features, hair, teeth, and eyes. In this work, we present Neural Parameterization (NeP), a hybrid representation that provides the advantages of both implicit and explicit methods. NeP is capable of photo-realistic rendering while allowing fine-grained editing of the scene geometry and appearance. We first disentangle the geometry and appearance by parameterizing the 3D geometry into 2D texture space. We enable geometric editability by introducing an explicit linear deformation blending layer. The deformation is controlled by a set of sparse key points, which can be explicitly and intuitively displaced to edit the geometry. For appearance, we develop a hybrid 2D texture consisting of an explicit texture map for easy editing and implicit view and time-dependent residuals to model temporal and view variations. We compare our method to several reconstruction and editing baselines. The results show that the NeP achieves almost the same level of rendering accuracy while maintaining high editability.

cs.CV↗

arXiv2022

Neural Color Operators for Sequential Image Retouching

We propose a novel image retouching method by modeling the retouching process as performing a sequence of newly introduced trainable neural color operators. The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar. To reflect the homomorphism property of color operators, we employ equivariant mapping and adopt an encoder-decoder structure which maps the non-linear color transformation to a much simpler transformation (i.e., translation) in a high dimensional space. The scalar strength of each neural color operator is predicted using CNN based strength predictors by analyzing global image statistics. Overall, our method is rather lightweight and offers flexible controls. Experiments and user studies on public datasets show that our method consistently achieves the best results compared with SOTA methods in both quantitative measures and visual qualities. The code and pretrained models are provided at https://github.com/amberwangyili/neurop

cs.CV↗

arXiv2022

Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing

This paper studies the computational offloading of CNN inference in dynamic multi-access edge computing (MEC) networks. To address the uncertainties in communication time and Edge servers' available capacity, we use early-exit mechanism to terminate the computation earlier to meet the deadline of inference tasks. We design a reward function to trade off the communication, computation and inference accuracy, and formulate the offloading problem of CNN inference as a maximization problem with the goal of maximizing the average inference accuracy and throughput in long term. To solve the maximization problem, we propose a graph reinforcement learning-based early-exit mechanism (GRLE), which outperforms the state-of-the-art work, deep reinforcement learning-based online offloading (DROO) and its enhanced method, DROO with early-exit mechanism (DROOE), under different dynamic scenarios. The experimental results show that GRLE achieves the average accuracy up to 3.41x over graph reinforcement learning (GRL) and 1.45x over DROOE, which shows the advantages of GRLE for offloading decision-making in dynamic MEC.

cs.LG↗

arXiv2022

RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction

Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages. Existing approaches generally focus on minimizing the distances between words in the aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. In addition, the mapping function is globally shared by all words, whose performance might be hindered by the deviations in the distributions of different languages. In this work, we propose a novel ranking-oriented induction model RAPO to learn personalized mapping function for each word. RAPO is capable of enjoying the merits from the unique characteristics of a single word and the cross-language isomorphism simultaneously. Extensive experimental results on public datasets including both rich-resource and low-resource languages demonstrate the superiority of our proposal. Our code is publicly available in \url{https://github.com/Jlfj345wf/RAPO}.

cs.CL↗

arXiv2022

Simultaneous Inference in Non-Sparse High-Dimensional Linear Models

Inference and prediction under the sparsity assumption have been a hot research topic in recent years. However, in practice, the sparsity assumption is difficult to test, and more importantly can usually be violated. In this paper, to study hypothesis test of any group of parameters under non-sparse high-dimensional linear models, we transform the null hypothesis to a testable moment condition and then use the self-normalization structure to construct moment test statistics under one-sample and two-sample cases, respectively. Compared to the one-sample case, the two-sample additionally requires a convolution condition. It is worth noticing that these test statistics contain Modified Dantzig Selector, which simultaneously estimates model parameters and error variance without sparse assumption. Specifically, our method can be extended to heavy tailed distributions of error for its robustness. On very mild conditions, we show that the probability of Type I error is asymptotically equal to the nominal level α and the probability of Type II error is asymptotically 0. Numerical experiments indicate that our proposed method has good finite-sample performance.

math.ST↗

arXiv2022

Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding

Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models. The current mainstream solution is designing an additional shallow model to pre-identify biased instances. However, such two-stage methods scale up the computational complexity of training process and obstruct valid feature information while mitigating bias. To address this issue, we utilize the representation normalization method which aims at disentangling the correlations between features of encoded sentences. We find it also promising in eliminating the bias problem by providing isotropic data distribution. We further propose Kernel-Whitening, a Nystrom kernel approximation method to achieve more thorough debiasing on nonlinear spurious correlations. Our framework is end-to-end with similar time consumption to fine-tuning. Experiments show that Kernel-Whitening significantly improves the performance of BERT on out-of-distribution datasets while maintaining in-distribution accuracy.

cs.CL↗

arXiv2022

PromptBERT: Improving BERT Sentence Embeddings with Prompts

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token embedding bias and ineffective BERT layers. Then we propose the first prompt-based sentence embeddings method and discuss two prompt representing methods and three prompt searching methods to make BERT achieve better sentence embeddings. Moreover, we propose a novel unsupervised training objective by the technology of template denoising, which substantially shortens the performance gap between the supervised and unsupervised settings. Extensive experiments show the effectiveness of our method. Compared to SimCSE, PromptBert achieves 2.29 and 2.58 points of improvement based on BERT and RoBERTa in the unsupervised setting.

cs.CL↗

arXiv2022

Charge-Density-Wave Proximity Effects in Graphene

Certain layered transition metal dichalcogenides (TMDCs), such as 1T-TaS2, show a rich collection of charge density wave (CDW) phases at different temperatures, and their atomic structures and electron conductions have been widely studied. However, the properties of CDW systems that are integrated with other electronic materials have not yet been investigated. Here, we incorporate the CDW properties of TMDCs into the electronic transport of graphene for the first time. During CDW phase transitions, anomalous transport behaviors that are closely related to the formation of correlated disorder in TMDCs were observed in the graphene sample used in this study. In particular, the commensurate CDW phase forms a periodic charge distribution with potential fluctuations, and thus constitutes correlated charged impurities, which decreases resistivity and enhances carrier mobility in graphene. The CDW-graphene heterostructure system demonstrated here paves the way to controlling the temperature-dependent carrier mobility and resistivity of graphene and to developing novel functional electronic devices such as graphene-based sensors and memory devices.

cond-mat.mes-hall↗