arXiv subjects

Wang

Publications and source records attributed to Wang.

At least 55 records · Page 3Linked to original sources

arXiv2022

Modeling Human Eye Movements with Neural Networks in a Maze-Solving Task

From smoothly pursuing moving objects to rapidly shifting gazes during visual search, humans employ a wide variety of eye movement strategies in different contexts. While eye movements provide a rich window into mental processes, building generative models of eye movements is notoriously difficult, and to date the computational objectives guiding eye movements remain largely a mystery. In this work, we tackled these problems in the context of a canonical spatial planning task, maze-solving. We collected eye movement data from human subjects and built deep generative models of eye movements using a novel differentiable architecture for gaze fixations and gaze shifts. We found that human eye movements are best predicted by a model that is optimized not to perform the task as efficiently as possible but instead to run an internal simulation of an object traversing the maze. This not only provides a generative model of eye movements in this task but also suggests a computational theory for how humans solve the task, namely that humans use mental simulation.

cs.LG↗

arXiv2022

LibFewShot: A Comprehensive Library for Few-shot Learning

Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some recent studies implicitly show that many generic techniques or ``tricks'', such as data augmentation, pre-training, knowledge distillation, and self-supervision, may greatly boost the performance of a few-shot learning method. Moreover, different works may employ different software platforms, backbone architectures and input image sizes, making fair comparisons difficult and practitioners struggle with reproducibility. To address these situations, we propose a comprehensive library for few-shot learning (LibFewShot) by re-implementing eighteen state-of-the-art few-shot learning methods in a unified framework with the same single codebase in PyTorch. Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks. In addition, with respect to the recent doubts on the necessity of meta- or episodic-training mechanism, our evaluation results confirm that such a mechanism is still necessary especially when combined with pre-training. We hope our work can not only lower the barriers for beginners to enter the area of few-shot learning but also elucidate the effects of nontrivial tricks to facilitate intrinsic research on few-shot learning. The source code is available from https://github.com/RL-VIG/LibFewShot.

cs.CV↗

arXiv2022

High Dimensional Latent Panel Quantile Regression with an Application to Asset Pricing

We propose a generalization of the linear panel quantile regression model to accommodate both \textit{sparse} and \textit{dense} parts: sparse means while the number of covariates available is large, potentially only a much smaller number of them have a nonzero impact on each conditional quantile of the response variable; while the dense part is represent by a low-rank matrix that can be approximated by latent factors and their loadings. Such a structure poses problems for traditional sparse estimators, such as the $\ell_1$-penalised Quantile Regression, and for traditional latent factor estimator, such as PCA. We propose a new estimation procedure, based on the ADMM algorithm, consists of combining the quantile loss function with $\ell_1$ \textit{and} nuclear norm regularization. We show, under general conditions, that our estimator can consistently estimate both the nonzero coefficients of the covariates and the latent low-rank matrix. Our proposed model has a "Characteristics + Latent Factors" Asset Pricing Model interpretation: we apply our model and estimator with a large-dimensional panel of financial data and find that (i) characteristics have sparser predictive power once latent factors were controlled (ii) the factors and coefficients at upper and lower quantiles are different from the median.

econ.EM↗

arXiv2022

Masked Co-attentional Transformer reconstructs 100x ultra-fast/low-dose whole-body PET from longitudinal images and anatomically guided MRI

Despite its tremendous value for the diagnosis, treatment monitoring and surveillance of children with cancer, whole body staging with positron emission tomography (PET) is time consuming and associated with considerable radiation exposure. 100x (1% of the standard clinical dosage) ultra-low-dose/ultra-fast whole-body PET reconstruction has the potential for cancer imaging with unprecedented speed and improved safety, but it cannot be achieved by the naive use of machine learning techniques. In this study, we utilize the global similarity between baseline and follow-up PET and magnetic resonance (MR) images to develop Masked-LMCTrans, a longitudinal multi-modality co-attentional CNN-Transformer that provides interaction and joint reasoning between serial PET/MRs of the same patient. We mask the tumor area in the referenced baseline PET and reconstruct the follow-up PET scans. In this manner, Masked-LMCTrans reconstructs 100x almost-zero radio-exposure whole-body PET that was not possible before. The technique also opens a new pathway for longitudinal radiology imaging reconstruction, a significantly under-explored area to date. Our model was trained and tested with Stanford PET/MRI scans of pediatric lymphoma patients and evaluated externally on PET/MRI images from Tübingen University. The high image quality of the reconstructed 100x whole-body PET images resulting from the application of Masked-LMCTrans will substantially advance the development of safer imaging approaches and shorter exam-durations for pediatric patients, as well as expand the possibilities for frequent longitudinal monitoring of these patients by PET.

eess.IV↗

arXiv2022

Bipolaronic nature of the pseudogap in (TaSe4)2I revealed via weak photoexcitation

The origin of the pseudogap in many strongly correlated materials has been a longstanding puzzle. Here, we uncover which many-body interactions underlie the pseudogap in quasi-one-dimensional (quasi-1D) material (TaSe4)2I by weak photo-excitation of the material to partially melt the ground state order and thereby reveal the underlying states in the gap. We observe the appearance of both dispersive and flat bands by using time- and angle-resolved photoemission spectroscopy. We assign the dispersive band to a single-particle bare band, while the flat band to a collection of single-polaron sub-bands. Our results provide direct experimental evidence that many-body interactions among small Holstein polarons i.e., the formation of bipolarons, are primarily responsible for the pseudogap in (TaSe4)2I. Recent theoretical studies of the Holstein model support the presence of such a bipolaron-to-polaron crossover. We also observe dramatically different relaxation times for the excited in-gap states in (TaSe4)2I (~600 fs) compared with another quasi-1D material Rb0.3MoO3 (~60 fs), which provides a new method for distinguishing between pseudogaps induced by polaronic or Luttinger-liquid many-body interactions.

cond-mat.str-el↗

arXiv2022

Multi-Modal Recurrent Fusion for Indoor Localization

This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB). By formulating the localization as a multi-modal sequence regression problem, a multi-stream recurrent fusion method is proposed to combine the current hidden state of each modality in the context of recurrent neural networks while accounting for the modality uncertainty which is directly learned from its own immediate past states. The proposed method was evaluated on the large-scale SPAWC2021 multi-modal localization dataset and compared with a wide range of baseline methods including the trilateration method, traditional fingerprinting methods, and convolution network-based methods.

eess.SP↗

arXiv2022

Multi-Band Wi-Fi Sensing with Matched Feature Granularity

Complementary to the fine-grained channel state information (CSI) from the physical layer and coarse-grained received signal strength indicator (RSSI) measurements, the mid-grained spatial beam attributes (e.g., beam SNR) that are available at millimeter-wave (mmWave) bands during the mandatory beam training phase can be repurposed for Wi-Fi sensing applications. In this paper, we propose a multi-band Wi-Fi fusion method for Wi-Fi sensing that hierarchically fuses the features from both the fine-grained CSI at sub-6 GHz and the mid-grained beam SNR at 60 GHz in a granularity matching framework. The granularity matching is realized by pairing two feature maps from the CSI and beam SNR at different granularity levels and linearly combining all paired feature maps into a fused feature map with learnable weights. To further address the issue of limited labeled training data, we propose an autoencoder-based multi-band Wi-Fi fusion network that can be pre-trained in an unsupervised fashion. Once the autoencoder-based fusion network is pre-trained, we detach the decoders and append multi-task sensing heads to the fused feature map by fine-tuning the fusion block and re-training the multi-task heads from the scratch. The multi-band Wi-Fi fusion framework is thoroughly validated by in-house experimental Wi-Fi sensing datasets spanning three tasks: 1) pose recognition; 2) occupancy sensing; and 3) indoor localization. Comparison to four baseline methods (i.e., CSI-only, beam SNR-only, input fusion, and feature fusion) demonstrates the granularity matching improves the multi-task sensing performance. Quantitative performance is evaluated as a function of the number of labeled training data, latent space dimension, and fine-tuning learning rates.

cs.NI↗

arXiv2022

Ultrasensitive electrode-free and co-catalyst-free detection of nanomoles per hour hydrogen evolution for the discovery of new photocatalysts

High throughput theoretical methods are increasingly used to identify promising photocatalytic materials for hydrogen generation from water as a clean source of energy. While most promising water splitting candidates require co-catalyst loading and electrical biasing, computational costs to predict them apriori becomes large. It is therefore important to identify bare, bias-free semiconductor photocatalysts with small initial hydrogen production rates, often in the range of tens of nano-mols per hour, as these can become highly efficient with further co-catalyst loading and biasing. Here we report a sensitive hydrogen detection system suitable for screening new photocatalysts. The hydrogen evolution rate of the prototypical rutile TiO2 loaded with 0.3 % wt Pt is detected to be 78.0+-0.8 μmol/h/0.04g, comparable with the rates reported in the literature. In contrast, sensitivity to an ultralow evolution rate of 11.4+-0.3 nmol/h/0.04g is demonstrated for bare polycrystalline TiO2 without electrical bias. Two candidate photocatalysts, ZnFe2O4 (18.1+-0.2 nmol/h/0.04g) and Ca2PbO4 (35.6+-0.5 nmol/h/0.04g), without electrical bias or co-catalyst loading, are demonstrated to be potentially superior to bare TiO2. This work expands the techniques available for sensitive detection of photocatalytic processes towards much faster screening of new candidate photocatalytic materials in their bare state

cond-mat.mtrl-sci↗

arXiv2021

VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)

Deep neural networks (DNNs) are prominent due to their superior performance in many fields. The deep-learning-as-a-service (DLaaS) paradigm enables individuals and organizations (clients) to outsource their DNN learning tasks to the cloud-based platforms. However, the DLaaS server may return incorrect DNN models due to various reasons (e.g., Byzantine failures). This raises the serious concern of how to verify if the DNN models trained by potentially untrusted DLaaS servers are indeed correct. To address this concern, in this paper, we design VeriDL, a framework that supports efficient correctness verification of DNN models in the DLaaS paradigm. The key idea of VeriDL is the design of a small-size cryptographic proof of the training process of the DNN model, which is associated with the model and returned to the client. Through the proof, VeriDL can verify the correctness of the DNN model returned by the DLaaS server with a deterministic guarantee and cheap overhead. Our experiments on four real-world datasets demonstrate the efficiency and effectiveness of VeriDL.

cs.CR↗

arXiv2021

Operon Dynamics with State Dependent Transcription and/or Translation Delays

Transcription and translation retrieve and operationalize gene encoded information in cells. These processes are not instantaneous and incur significant delays. In this paper we study Goodwin models of both inducible and repressible operons with state-dependent delays. The paper provides justification and derivation of the model, detailed analysis of the appropriate setting of the corresponding dynamical system, and extensive numerical analysis of its dynamics. Comparison with constant delay models shows significant differences in dynamics that include existence of stable periodic orbits in inducible systems and multistability in repressible systems. A combination of parameter space exploration, numerics, analysis of steady state linearization and bifurcation theory indicates the likely presence of Shilnikov-type homoclinic bifurcations in the repressible operon model.

math.DS↗

arXiv2021

Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss

Cyber attacks pose crucial threats to computer system security, and put digital treasuries at excessive risks. This leads to an urgent call for an effective intrusion detection system that can identify the intrusion attacks with high accuracy. It is challenging to classify the intrusion events due to the wide variety of attacks. Furthermore, in a normal network environment, a majority of the connections are initiated by benign behaviors. The class imbalance issue in intrusion detection forces the classifier to be biased toward the majority/benign class, thus leave many attack incidents undetected. Spurred by the success of deep neural networks in computer vision and natural language processing, in this paper, we design a new system named DeepIDEA that takes full advantage of deep learning to enable intrusion detection and classification. To achieve high detection accuracy on imbalanced data, we design a novel attack-sharing loss function that can effectively move the decision boundary towards the attack classes and eliminates the bias towards the majority/benign class. By using this loss function, DeepIDEA respects the fact that the intrusion mis-classification should receive higher penalty than the attack mis-classification. Extensive experimental results on three benchmark datasets demonstrate the high detection accuracy of DeepIDEA. In particular, compared with eight state-of-the-art approaches, DeepIDEA always provides the best class-balanced accuracy.

cs.CR↗

arXiv2021

Compact Molecular Gas Distribution in Quasar Host Galaxies

We use Atacama Large Millimeter/submillimeter Array CO(2-1) observations of six low-redshift Palomar-Green quasars to study the distribution and kinematics of the molecular gas of their host galaxies at kpc-scale resolution. While the molecular gas content, molecular gas fraction, and star formation rates are similar to those of nearby massive, star-forming galaxies, the quasar host galaxies possess exceptionally compact, disky molecular gas distributions with a median half-light radius of 1.8 kpc and molecular gas mass surface densities $\gtrsim 22$ $M_\odot$pc$^{-2}$. While the overall velocity field of the molecular gas is dominated by regular rotation out to large radii, with rotation velocity-to-velocity dispersion ratio $\gtrsim 9$, the nuclear region displays substantial kinematic complexity associated with small-scale substructure in the gas distribution. A tilted-ring analysis reveals that the kinematic and photometric position angles are misaligned on average by $\sim 34 \pm 26^\circ$, and provides evidence of kinematic twisting. These observations provide tantalizing clues to the detailed physical conditions of the circumnuclear environments of actively accreting supermassive black holes.

astro-ph.GA↗

arXiv2020

An adversarial learning framework for preserving users' anonymity in face-based emotion recognition

Image and video-capturing technologies have permeated our every-day life. Such technologies can continuously monitor individuals' expressions in real-life settings, affording us new insights into their emotional states and transitions, thus paving the way to novel well-being and healthcare applications. Yet, due to the strong privacy concerns, the use of such technologies is met with strong skepticism, since current face-based emotion recognition systems relying on deep learning techniques tend to preserve substantial information related to the identity of the user, apart from the emotion-specific information. This paper proposes an adversarial learning framework which relies on a convolutional neural network (CNN) architecture trained through an iterative procedure for minimizing identity-specific information and maximizing emotion-dependent information. The proposed approach is evaluated through emotion classification and face identification metrics, and is compared against two CNNs, one trained solely for emotion recognition and the other trained solely for face identification. Experiments are performed using the Yale Face Dataset and Japanese Female Facial Expression Database. Results indicate that the proposed approach can learn a convolutional transformation for preserving emotion recognition accuracy and degrading face identity recognition, providing a foundation toward privacy-aware emotion recognition technologies.

cs.LG↗

arXiv2019

Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models

Deep Neural Networks (DNNs) are vulnerable to deliberately crafted adversarial examples. In the past few years, many efforts have been spent on exploring query-optimisation attacks to find adversarial examples of either black-box or white-box DNN models, as well as the defending countermeasures against those attacks. In this work, we explore vulnerabilities of DNN models under the umbrella of Man-in-the-Middle (MitM) attacks, which has not been investigated before. From the perspective of an MitM adversary, the aforementioned adversarial example attacks are not viable anymore. First, such attacks must acquire the outputs from the models by multiple times before actually launching attacks, which is difficult for the MitM adversary in practice. Second, such attacks are one-off and cannot be directly generalised onto new data examples, which decreases the rate of return for the attacker. In contrast, using generative models to craft adversarial examples on the fly can mitigate the drawbacks. However, the adversarial capability of the generative models, such as Variational Auto-Encoder (VAE), has not been extensively studied. Therefore, given a classifier, we investigate using a VAE decoder to either transform benign inputs to their adversarial counterparts or decode outputs from benign VAE encoders to be adversarial examples. The proposed method can endue more capability to MitM attackers. Based on our evaluation, the proposed attack can achieve above 95% success rate on both MNIST and CIFAR10 datasets, which is better or comparable with state-of-the-art query-optimisation attacks. At the meantime, the attack is 104 times faster than the query-optimisation attacks.

cs.CR↗

arXiv2019

Improved Super-Resolution Convolution Neural Network for Large Images

Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value. In daily life, we crop a large image into sub-images to do super-resolution and then merge them together. Although convolution neural network performs very well in the research field, if we use it to do super-resolution, we can easily observe cutting lines from merged pictures. To address these problems, in this paper, we propose a refined architecture of SRCNN with 'Symmetric padding', 'Random learning' and 'Residual learning'. Moreover, we have done a lot of experiments to prove our model performs best among a lot of the state-of-art methods.

cs.CV↗

arXiv2019

Measuring Average Treatment Effect from Heavy-tailed Data

Heavy-tailed metrics are common and often critical to product evaluation in the online world. While we may have samples large enough for Central Limit Theorem to kick in, experimentation is challenging due to the wide confidence interval of estimation. We demonstrate the pressure by running A/A simulations with customer spending data from a large-scale Ecommerce site. Solutions are then explored. On one front we address the heavy tail directly and highlight the often ignored nuances of winsorization. In particular, the legitimacy of false positive rate could be at risk. We are further inspired by the idea of robust statistics and introduce Huber regression as a better way to measure treatment effect. On another front covariates from pre-experiment period are exploited. Although they are independent to assignment and potentially explain the variation of response well, concerns are that models are learned against prediction error rather than the bias of parameter. We find the framework of orthogonal learning useful, matching not raw observations but residuals from two predictions, one towards the response and the other towards the assignment. Robust regression is readily integrated, together with cross-fitting. The final design is proven highly effective in driving down variance at the same time controlling bias. It is empowering our daily practice and hopefully can also benefit other applications in the industry.

stat.AP↗

arXiv2018

Cost-efficient Data Acquisition on Online Data Marketplaces for Correlation Analysis

Incentivized by the enormous economic profits, the data marketplace platform has been proliferated recently. In this paper, we consider the data marketplace setting where a data shopper would like to buy data instances from the data marketplace for correlation analysis of certain attributes. We assume that the data in the marketplace is dirty and not free. The goal is to find the data instances from a large number of datasets in the marketplace whose join result not only is of high-quality and rich join informativeness, but also delivers the best correlation between the requested attributes. To achieve this goal, we design DANCE, a middleware that provides the desired data acquisition service. DANCE consists of two phases: (1) In the off-line phase, it constructs a two-layer join graph from samples. The join graph consists of the information of the datasets in the marketplace at both schema and instance levels; (2) In the online phase, it searches for the data instances that satisfy the constraints of data quality, budget, and join informativeness, while maximize the correlation of source and target attribute sets. We prove that the complexity of the search problem is NP-hard, and design a heuristic algorithm based on Markov chain Monte Carlo (MCMC). Experiment results on two benchmark datasets demonstrate the efficiency and effectiveness of our heuristic data acquisition algorithm.

cs.DB↗

arXiv2018

Truth Inference on Sparse Crowdsourcing Data with Local Differential Privacy

Crowdsourcing has arisen as a new problem-solving paradigm for tasks that are difficult for computers but easy for humans. However, since the answers collected from the recruited participants (workers) may contain sensitive information, crowdsourcing raises serious privacy concerns. In this paper, we investigate the problem of protecting answer privacy under local differential privacy (LDP), by which individual workers randomize their answers independently and send the perturbed answers to the task requester. The utility goal is to enable to infer the true answer (i.e., truth) from the perturbed data with high accuracy. One of the challenges of LDP perturbation is the sparsity of worker answers (i.e., each worker only answers a small number of tasks). Simple extension of the existing approaches (e.g., Laplace perturbation and randomized response) may incur large error of truth inference on sparse data. Thus we design an efficient new matrix factorization (MF) algorithm under LDP. We prove that our MF algorithm can provide both LDP guarantee and small error of truth inference, regardless of the sparsity of worker answers. We perform extensive experiments on real-world and synthetic datasets, and demonstrate that the MF algorithm performs better than the existing LDP algorithms on sparse crowdsourcing data.

cs.CR↗