arXiv subjects

Hui Liu

Publications and source records attributed to Hui Liu.

At least 451 records · Page 25Linked to original sources

arXiv2022

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels

Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges and limited labeled nodes could harm the message-passing mechanism of GNNs. To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes. The generated edges are further used to regularize the predictions of unlabeled nodes with label smoothness to better train GNNs. Experimental results on real-world datasets demonstrate the robustness of the proposed framework on noisy graphs with limited labeled nodes.

cs.LG↗

arXiv2022

Interpretable Low-Resource Legal Decision Making

Over the past several years, legal applications of deep learning have been on the rise. However, as with other high-stakes decision making areas, the requirement for interpretability is of crucial importance. Current models utilized by legal practitioners are more of the conventional machine learning type, wherein they are inherently interpretable, yet unable to harness the performance capabilities of data-driven deep learning models. In this work, we utilize deep learning models in the area of trademark law to shed light on the issue of likelihood of confusion between trademarks. Specifically, we introduce a model-agnostic interpretable intermediate layer, a technique which proves to be effective for legal documents. Furthermore, we utilize weakly supervised learning by means of a curriculum learning strategy, effectively demonstrating the improved performance of a deep learning model. This is in contrast to the conventional models which are only able to utilize the limited number of expensive manually-annotated samples by legal experts. Although the methods presented in this work tackles the task of risk of confusion for trademarks, it is straightforward to extend them to other fields of law, or more generally, to other similar high-stakes application scenarios.

cs.LG↗

arXiv2021

Nuclear Fermi Momenta of $^{2}$H, $^{27}$Al and $^{56}$Fe from an Analysis of CLAS data

Nuclear Fermi momentum is a basic property of a nucleus where many nucleons dwell. However, in experiments only the nuclear Fermi momenta of just a few nuclei are measured using quasielastic electron scattering on the nuclear targets so far. Particularly, we still do not know experimentally the Fermi momentum of the lightest nucleon composite -- the deuteron. In this paper, we apply both gaussian distribution and Cauchy distribution to describe the quasielastic peak in the cross section of electron-nucleus scattering. The dip of the cross-section ratio at about $x_{\rm B}=1$ is explained with the nuclear Fermi momentum. By performing the least-square fits to the published CLAS data in the narrow kinematic region of quasielastic scattering, we obtain the nuclear Fermi momenta of $^{2}$H, $^{27}$Al and $^{56}$Fe, which are $116\pm 7$ MeV/c, $232\pm 27$ MeV/c, and $244\pm 28$ MeV/c respectively. The extracted nuclear Fermi momenta are compared to the simple calculations based on Fermi gas model, and the consistencies are found.

nucl-th↗

arXiv2021

Magnetoconductance modulations due to interlayer tunneling in radial superlattices

Radial superlattices are nanostructured materials obtained by rolling-up thin solid films into spiral-like tubular structures. The formation of these "high-order" superlattices from two-dimensional crystals or ultrathin films is expected to result in a transition of transport characteristics from two-dimensional to one-dimensional. Here, we show that a transport hallmark of radial superlattices is the appearance of magnetoconductance modulations in the presence of externally applied axial magnetic fields. This phenomenon critically relies on electronic interlayer tunneling processes that activates an unconventional Aharonov-Bohm-like effect. Using a combination of density functional theory calculations and low-energy continuum models, we determine the electronic states of a paradigmatic single-material radial superlattice -- a two-winding carbon nanoscroll -- and indeed show momentum-dependent oscillations of the magnetic states in axial configuration, which we demonstrate to be entirely due to hopping between the two windings of the spiral-shaped scroll.

cond-mat.mtrl-sci↗

arXiv2021

GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial Attack

Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs). Existing works synthesize adversarial examples by leveraging simple metrics to penalize perturbations, that lack sufficient consideration of the human visual system (HVS), which produces noticeable artifacts. To explore why the perturbations are visible, this paper summarizes four primary factors affecting the perceptibility of human eyes. Based on this investigation, we design a multi-factor metric MulFactorLoss for measuring the perceptual loss between benign examples and adversarial ones. In order to test the imperceptibility of the multi-factor metric, we propose a novel black-box adversarial attack that is referred to as GreedyFool. GreedyFool applies differential evolution to evaluate the effects of perturbed pixels on the confidence of a target DNN, and introduces greedy approximation to automatically generate adversarial perturbations. We conduct extensive experiments on the ImageNet and CIFRA-10 datasets and a comprehensive user study with 60 participants. The experimental results demonstrate that MulFactorLoss is a more imperceptible metric than the existing pixelwise metrics, and GreedyFool achieves a 100% success rate in a black-box manner.

cs.LG↗

arXiv2021

Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features

Deep neural networks (DNNs) are under threat from adversarial example attacks. The adversary can easily change the outputs of DNNs by adding small well-designed perturbations to inputs. Adversarial example detection is a fundamental work for robust DNNs-based service. Adversarial examples show the difference between humans and DNNs in image recognition. From a human-centric perspective, image features could be divided into dominant features that are comprehensible to humans, and recessive features that are incomprehensible to humans, yet are exploited by DNNs. In this paper, we reveal that imperceptible adversarial examples are the product of recessive features misleading neural networks, and an adversarial attack is essentially a kind of method to enrich these recessive features in the image. The imperceptibility of the adversarial examples indicates that the perturbations enrich recessive features, yet hardly affect dominant features. Therefore, adversarial examples are sensitive to filtering off recessive features, while benign examples are immune to such operation. Inspired by this idea, we propose a label-only adversarial detection approach that is referred to as feature-filter. Feature-filter utilizes discrete cosine transform to approximately separate recessive features from dominant features, and gets a mutant image that is filtered off recessive features. By only comparing DNN's prediction labels on the input and its mutant, feature-filter can real-time detect imperceptible adversarial examples at high accuracy and few false positives.

cs.LG↗

arXiv2021

Quantum mechanics of fermion confined to a curved surface in Foldy-Wouthuysen representation

In Foldy-Wouthuysen representation, we deduce the effective quantum mechanics for a particle confined to a curved surface by using the thin-layer quantization scheme. We find that the spin effect caused by confined potential as the results of relativistic correction in the non-relativistic limit. Furthermore, the spin connection appeared in curved surface which depends on curvature contributes a Zeeman-like gap in the relativistic correction term. In addition, the confined potential also induces a curvature-independent energy shift, which is from the zitterbewegung effect. As an example, we apply the effective Hamiltonian to torus surface, in which we obtain expectantly the spin effects related to confined potential. Those results directly demonstrate the scaling of the uncommutation of the non-relativistic limit and the thin-layer quantization formalism

quant-ph↗

arXiv2021

Acoustic topological Anderson insulators

Recent breakthrough on topological Anderson insulators revealed the breakdown of the traditional perception that sufficiently strong disorder may induce the appearance of topological protected transport states instead of destruction. Although topological Anderson insulators have been observed in various time-reversal symmetry breaking systems, the observation of topological Anderson insulators protected by time-reversal symmetry remains scarce, which are considered to be more promising in applications such as the integrated devices. Here, we report the experimental observation of topological Anderson insulator in a two-dimensional bilayer phononic crystal. The robust spin-dependent edge states, as evidence of topological Anderson insulating phase, are observed by introducing on-site disorder. In addition, spin Bott index was computed to identify the topological invariants of the system with disorder, which confirmed the occurrence of disorder-induced topological state. Our results reveal that the impurities and defects introduced in the processing of integrated devices may induce the formation of topological transport states, which are promising for the exploration of new routes for the integration devices design.

cond-mat.mes-hall↗

arXiv2021

Toward Annotator Group Bias in Crowdsourcing

Crowdsourcing has emerged as a popular approach for collecting annotated data to train supervised machine learning models. However, annotator bias can lead to defective annotations. Though there are a few works investigating individual annotator bias, the group effects in annotators are largely overlooked. In this work, we reveal that annotators within the same demographic group tend to show consistent group bias in annotation tasks and thus we conduct an initial study on annotator group bias. We first empirically verify the existence of annotator group bias in various real-world crowdsourcing datasets. Then, we develop a novel probabilistic graphical framework GroupAnno to capture annotator group bias with a new extended Expectation Maximization (EM) training algorithm. We conduct experiments on both synthetic and real-world datasets. Experimental results demonstrate the effectiveness of our model in modeling annotator group bias in label aggregation and model learning over competitive baselines.

cs.HC↗

arXiv2021

Hidden Backdoors in Human-Centric Language Models

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick the model into producing unexpected behaviors. In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. We deploy our hidden backdoors through two state-of-the-art trigger embedding methods. The first approach via homograph replacement, embeds the trigger into deep neural networks through the visual spoofing of lookalike character replacement. The second approach uses subtle differences between text generated by language models and real natural text to produce trigger sentences with correct grammar and high fluency. We demonstrate that the proposed hidden backdoors can be effective across three downstream security-critical NLP tasks, representative of modern human-centric NLP systems, including toxic comment detection, neural machine translation (NMT), and question answering (QA). Our two hidden backdoor attacks can achieve an Attack Success Rate (ASR) of at least $97\%$ with an injection rate of only $3\%$ in toxic comment detection, $95.1\%$ ASR in NMT with less than $0.5\%$ injected data, and finally $91.12\%$ ASR against QA updated with only 27 poisoning data samples on a model previously trained with 92,024 samples (0.029\%). We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.

cs.CL↗

arXiv2021

Geometry-induced Monopole Magnetic Field and Quantum Spin Hall Effect

The geometric effects of two-dimensional curved systems have been an interesting topic for a long time. A Möbius surface is specifically considered. For a relativistic particle confined to the nontrivial surface, we give the effective Dirac equation in the thin-layer quantization formalism, and we find a geometric gauge potential that results from the rotation transformation of the local frame moving on Möbius strip, and an effective mass that is from the rescaling transformation. Intriguingly, the geometric gauge potential can play a role of monopole magnetic field for the particles with spin, and which can produce quantum spin Hall effects. As potential applications, effective monopole magnetic fields and spin Hall phenomena can be generated and manipulated by designing the geometries and topologies of two-dimensional nanodevices.

quant-ph↗

arXiv2021

Unsupervised Conversation Disentanglement through Co-Training

Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on conversation disentanglement relies heavily upon human-annotated datasets, which are expensive to obtain in practice. In this work, we explore to train a conversation disentanglement model without referencing any human annotations. Our method is built upon a deep co-training algorithm, which consists of two neural networks: a message-pair classifier and a session classifier. The former is responsible for retrieving local relations between two messages while the latter categorizes a message to a session by capturing context-aware information. Both networks are initialized respectively with pseudo data built from an unannotated corpus. During the deep co-training process, we use the session classifier as a reinforcement learning component to learn a session assigning policy by maximizing the local rewards given by the message-pair classifier. For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier. Experimental results on the large Movie Dialogue Dataset demonstrate that our proposed approach achieves competitive performance compared to the previous supervised methods. Further experiments show that the predicted disentangled conversations can promote the performance on the downstream task of multi-party response selection.

cs.CL↗

arXiv2021

Double-bowl State in photonic Dirac nodal line semimetal

The past decade has seen a proliferation of topological materials for both insulators and semimetals in electronic systems and classical waves. Topological semimetals exhibit topologically protected band degeneracies, such as nodal points and nodal lines. Dirac nodal line semimetals (DNLS), which own four-fold line degeneracy, have drawn particular attention. DNLSs have been studied in electronic systems but there is no photonic DNLS. Here in this work, we provide a new mechanism which is unique for photonic systems to investigate a stringent photonic DNLS. When truncated, the photonic DNLS exhibits double-bowl states (DBS), which comprises two sets of perpendicularly polarized surface states. In sharp contrast to nondegenerate surface states in other photonic systems, here the two sets of surface states are almost degenerate over the whole spectrum range. The DBS and the bulk Dirac nodal ring (DNR) dispersion along the relevant directions, are experimentally resolved.

physics.optics↗

arXiv2021

Learning Dynamic Interpolation for Extremely Sparse Light Fields with Wide Baselines

In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation. Specifically, with the estimated geometric relation between input views, we first construct a lightweight neural network to dynamically learn weights for interpolating neighbouring pixels from input views to synthesize each pixel of novel views independently. In contrast to the fixed and content-independent weights employed in the geometry warping operation, the learned interpolation weights implicitly incorporate the correspondences between the source and novel views and adapt to different image content information. Then, we recover the spatial correlation between the independently synthesized pixels of each novel view by referring to that of input views using a geometry-based spatial refinement module. We also constrain the angular correlation between the novel views through a disparity-oriented LF structure loss. Experimental results on LF datasets with wide baselines show that the reconstructed LFs achieve much higher PSNR/SSIM and preserve the LF parallax structure better than state-of-the-art methods. The source code is publicly available at https://github.com/MantangGuo/DI4SLF.

cs.CV↗

arXiv2021

Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild

This paper investigates the problem of reconstructing hyperspectral (HS) images from single RGB images captured by commercial cameras, \textbf{without} using paired HS and RGB images during training. To tackle this challenge, we propose a new lightweight and end-to-end learning-based framework. Specifically, on the basis of the intrinsic imaging degradation model of RGB images from HS images, we progressively spread the differences between input RGB images and re-projected RGB images from recovered HS images via effective unsupervised camera spectral response function estimation. To enable the learning without paired ground-truth HS images as supervision, we adopt the adversarial learning manner and boost it with a simple yet effective $\mathcal{L}_1$ gradient clipping scheme. Besides, we embed the semantic information of input RGB images to locally regularize the unsupervised learning, which is expected to promote pixels with identical semantics to have consistent spectral signatures. In addition to conducting quantitative experiments over two widely-used datasets for HS image reconstruction from synthetic RGB images, we also evaluate our method by applying recovered HS images from real RGB images to HS-based visual tracking. Extensive results show that our method significantly outperforms state-of-the-art unsupervised methods and even exceeds the latest supervised method under some settings. The source code is public available at https://github.com/zbzhzhy/Unsupervised-Spectral-Reconstruction.

cs.CV↗

arXiv2021

Graph2MDA: a multi-modal variational graph embedding model for predicting microbe-drug associations

Accumulated clinical studies show that microbes living in humans interact closely with human hosts, and get involved in modulating drug efficacy and drug toxicity. Microbes have become novel targets for the development of antibacterial agents. Therefore, screening of microbe-drug associations can benefit greatly drug research and development. With the increase of microbial genomic and pharmacological datasets, we are greatly motivated to develop an effective computational method to identify new microbe-drug associations. In this paper, we proposed a novel method, Graph2MDA, to predict microbe-drug associations by using variational graph autoencoder (VGAE). We constructed multi-modal attributed graphs based on multiple features of microbes and drugs, such as molecular structures, microbe genetic sequences, and function annotations. Taking as input the multi-modal attribute graphs, VGAE was trained to learn the informative and interpretable latent representations of each node and the whole graph, and then a deep neural network classifier was used to predict microbe-drug associations. The hyperparameter analysis and model ablation studies showed the sensitivity and robustness of our model. We evaluated our method on three independent datasets and the experimental results showed that our proposed method outperformed six existing state-of-the-art methods. We also explored the meaningness of the learned latent representations of drugs and found that the drugs show obvious clustering patterns that are significantly consistent with drug ATC classification. Moreover, we conducted case studies on two microbes and two drugs and found 75\%-95\% predicted associations have been reported in PubMed literature. Our extensive performance evaluations validated the effectiveness of our proposed method.\

q-bio.QM↗

arXiv2021

Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images

This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretable, compact, efficient, and end-to-end learning-based framework, namely AGD-Net. Precisely, by taking advantage of the imaging process, we first formulate the problem explicitly based on the classic gradient descent algorithm. Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient. Besides, based on the approximate low-rank property of HS images, we propose a novel rank loss to promote the similarity between the global structures of reconstructed and ground-truth HS images, which is optimized with our singular value weighting strategy during training. Moreover, AGD-Net, a single network after one-time training, is flexible to handle the reconstruction with various spectral response functions. Extensive experiments over three commonly-used benchmark datasets demonstrate that AGD-Net can improve the reconstruction quality by more than 1.0 dB on average while saving 67$\times$ parameters and 32$\times$ FLOPs, compared with state-of-the-art methods. The code will be publicly available at https://github.com/zbzhzhy/GD-Net.

eess.IV↗

arXiv2021

Attention-driven Graph Clustering Network

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph convolutional network captures the topological graph feature. However, the existing works (i) lack a flexible combination mechanism to adaptively fuse those two kinds of features for learning the discriminative representation and (ii) overlook the multi-scale information embedded at different layers for subsequent cluster assignment, leading to inferior clustering results. To this end, we propose a novel deep clustering method named Attention-driven Graph Clustering Network (AGCN). Specifically, AGCN exploits a heterogeneity-wise fusion module to dynamically fuse the node attribute feature and the topological graph feature. Moreover, AGCN develops a scale-wise fusion module to adaptively aggregate the multi-scale features embedded at different layers. Based on a unified optimization framework, AGCN can jointly perform feature learning and cluster assignment in an unsupervised fashion. Compared with the existing deep clustering methods, our method is more flexible and effective since it comprehensively considers the numerous and discriminative information embedded in the network and directly produces the clustering results. Extensive quantitative and qualitative results on commonly used benchmark datasets validate that our AGCN consistently outperforms state-of-the-art methods.

cs.CV↗