arXiv subjects

Bo Han

Publications and source records attributed to Bo Han.

At least 307 records · Page 17Linked to original sources

arXiv2022

Robust Weight Perturbation for Adversarial Training

Overfitting widely exists in adversarial robust training of deep networks. An effective remedy is adversarial weight perturbation, which injects the worst-case weight perturbation during network training by maximizing the classification loss on adversarial examples. Adversarial weight perturbation helps reduce the robust generalization gap; however, it also undermines the robustness improvement. A criterion that regulates the weight perturbation is therefore crucial for adversarial training. In this paper, we propose such a criterion, namely Loss Stationary Condition (LSC) for constrained perturbation. With LSC, we find that it is essential to conduct weight perturbation on adversarial data with small classification loss to eliminate robust overfitting. Weight perturbation on adversarial data with large classification loss is not necessary and may even lead to poor robustness. Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation. The perturbation strategy prevents deep networks from overfitting while avoiding the side effect of excessive weight perturbation, significantly improving the robustness of adversarial training. Extensive experiments demonstrate the superiority of the proposed method over the state-of-the-art adversarial training methods.

cs.LG↗

arXiv2022

FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels

Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices. Hence, the labels in practice are usually annotated by clients of varying expertise or criteria and thus contain different amounts of noises. Local training on noisy labels can easily result in overfitting to noisy labels, which is devastating to the global model through aggregation. Although recent robust FL methods take malicious clients into account, they have not addressed local noisy labels on each device and the impact to the global model. In this paper, we develop a simple two-level sampling method "FedNoiL" that (1) selects clients for more robust global aggregation on the server; and (2) selects clean labels and correct pseudo-labels at the client end for more robust local training. The sampling probabilities are built upon clean label detection by the global model. Moreover, we investigate different schedules changing the local epochs between aggregations over the course of FL, which notably improves the communication and computation efficiency in noisy label setting. In experiments with homogeneous/heterogeneous data distributions and noise ratios, we observed that direct combinations of SOTA FL methods with SOTA noisy-label learning methods can easily fail but our method consistently achieves better and robust performance.

cs.LG↗

arXiv2022

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

Pluralistic image completion focuses on generating both visually realistic and diverse results for image completion. Prior methods enjoy the empirical successes of this task. However, their used constraints for pluralistic image completion are argued to be not well interpretable and unsatisfactory from two aspects. First, the constraints for visual reality can be weakly correlated to the objective of image completion or even redundant. Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well. In this paper, to address the issues, we propose an end-to-end probabilistic method. Specifically, we introduce a unified probabilistic graph model that represents the complex interactions in image completion. The entire procedure of image completion is then mathematically divided into several sub-procedures, which helps efficient enforcement of constraints. The sub-procedure directly related to pluralistic results is identified, where the interaction is established by a Gaussian mixture model (GMM). The inherent parameters of GMM are task-related, which are optimized adaptively during training, while the number of its primitives can control the diversity of results conveniently. We formally establish the effectiveness of our method and demonstrate it with comprehensive experiments.

cs.CV↗

arXiv2022

Low-rank Tensor Learning with Nonconvex Overlapped Nuclear Norm Regularization

Nonconvex regularization has been popularly used in low-rank matrix learning. However, extending it for low-rank tensor learning is still computationally expensive. To address this problem, we develop an efficient solver for use with a nonconvex extension of the overlapped nuclear norm regularizer. Based on the proximal average algorithm, the proposed algorithm can avoid expensive tensor folding/unfolding operations. A special "sparse plus low-rank" structure is maintained throughout the iterations, and allows fast computation of the individual proximal steps. Empirical convergence is further improved with the use of adaptive momentum. We provide convergence guarantees to critical points on smooth losses and also on objectives satisfying the Kurdyka-Łojasiewicz condition. While the optimization problem is nonconvex and nonsmooth, we show that its critical points still have good statistical performance on the tensor completion problem. Experiments on various synthetic and real-world data sets show that the proposed algorithm is efficient in both time and space and more accurate than the existing state-of-the-art.

cs.LG↗

arXiv2022

Brightening of a dark monolayer semiconductor via strong light-matter coupling in a cavity

Engineering the properties of quantum materials via strong light-matter coupling is a compelling research direction with a multiplicity of modern applications. Those range from modifying charge transport in organic molecules, steering particle correlation and interactions, and even controlling chemical reactions. Here, we study the modification of the material properties via strong coupling and demonstrate an effective inversion of the excitonic band-ordering in a monolayer of WSe2 with spin-forbidden, optically dark ground state. In our experiments, we harness the strong light-matter coupling between cavity photon and the high energy, spin-allowed bright exciton, and thus creating two bright polaritonic modes in the optical bandgap with the lower polariton mode pushed below the WSe2 dark state. We demonstrate that in this regime the commonly observed luminescence quenching stemming from the fast relaxation to the dark ground state is prevented, which results in the brightening of this intrinsically dark material. We probe this effective brightening by temperature-dependent photoluminescence, and we find an excellent agreement with a theoretical model accounting for the inversion of the band ordering and phonon-assisted polariton relaxation.

cond-mat.mes-hall↗

arXiv2022

A gate-programmable van der Waals metal-ferroelectric-semiconductor memory

Ferroelecticity, one of the keys to realize nonvolatile memories owing to the remanent electric polarization, has been an emerging phenomenon in the two-dimensional (2D) limit. Yet the demonstrations of van der Waals (vdW) memories using 2D ferroelectric materials as an ingredient are very limited. Especially, gate-tunable ferroelectric vdW memristive device, which holds promises in future neuromorphic applications, remains challenging. Here, we show a prototype gate-programmable memory by vertically assembling graphite, CuInP2S6, and MoS2 layers into a metal-ferroelectric-semiconductor architecture. The resulted devices exhibit two-terminal switchable electro-resistance with on-off ratios exceeding 105 and long-term retention, akin to a conventional memristor but strongly coupled to the ferroelectric characteristics of the CuInP2S6 layer. By controlling the top gate, Fermi level of MoS2 can be set inside (outside) of its band gap to quench (enable) the memristive behaviour, yielding a three-terminal gate programmable nonvolatile vdW memory. Our findings pave the way for the engineering of ferroelectric-mediated memories in future implementations of nanoelectronics.

cond-mat.mtrl-sci↗

arXiv2022

Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

Recently Graph Injection Attack (GIA) emerges as a practical attack scenario on Graph Neural Networks (GNNs), where the adversary can merely inject few malicious nodes instead of modifying existing nodes or edges, i.e., Graph Modification Attack (GMA). Although GIA has achieved promising results, little is known about why it is successful and whether there is any pitfall behind the success. To understand the power of GIA, we compare it with GMA and find that GIA can be provably more harmful than GMA due to its relatively high flexibility. However, the high flexibility will also lead to great damage to the homophily distribution of the original graph, i.e., similarity among neighbors. Consequently, the threats of GIA can be easily alleviated or even prevented by homophily-based defenses designed to recover the original homophily. To mitigate the issue, we introduce a novel constraint -- homophily unnoticeability that enforces GIA to preserve the homophily, and propose Harmonious Adversarial Objective (HAO) to instantiate it. Extensive experiments verify that GIA with HAO can break homophily-based defenses and outperform previous GIA attacks by a significant margin. We believe our methods can serve for a more reliable evaluation of the robustness of GNNs.

cs.LG↗

arXiv2022

Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning \mbox{methods} with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts.

cs.LG↗

arXiv2022

Probabilistic Margins for Instance Reweighting in Adversarial Training

Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i.e., they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighting adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e.g., such the probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrate that PMs are reliable measurements and PM-based reweighting methods outperform state-of-the-art methods.

cs.LG↗

arXiv2022

DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets

Mobile headsets should be capable of understanding 3D physical environments to offer a truly immersive experience for augmented/mixed reality (AR/MR). However, their small form-factor and limited computation resources make it extremely challenging to execute in real-time 3D vision algorithms, which are known to be more compute-intensive than their 2D counterparts. In this paper, we propose DeepMix, a mobility-aware, lightweight, and hybrid 3D object detection framework for improving the user experience of AR/MR on mobile headsets. Motivated by our analysis and evaluation of state-of-the-art 3D object detection models, DeepMix intelligently combines edge-assisted 2D object detection and novel, on-device 3D bounding box estimations that leverage depth data captured by headsets. This leads to low end-to-end latency and significantly boosts detection accuracy in mobile scenarios. A unique feature of DeepMix is that it fully exploits the mobility of headsets to fine-tune detection results and boost detection accuracy. To the best of our knowledge, DeepMix is the first 3D object detection that achieves 30 FPS (an end-to-end latency much lower than the 100 ms stringent requirement of interactive AR/MR). We implement a prototype of DeepMix on Microsoft HoloLens and evaluate its performance via both extensive controlled experiments and a user study with 30+ participants. DeepMix not only improves detection accuracy by 9.1--37.3% but also reduces end-to-end latency by 2.68--9.15x, compared to the baseline that uses existing 3D object detection models.

cs.CV↗

arXiv2022

Reliable Adversarial Distillation with Unreliable Teachers

In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are stronger supervision than the original hard labels. However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students. Therefore, in this paper, we propose reliable introspective adversarial distillation (IAD) where students partially instead of fully trust their teachers. Specifically, IAD distinguishes between three cases given a query of a natural data (ND) and the corresponding adversarial data (AD): (a) if a teacher is good at AD, its SL is fully trusted; (b) if a teacher is good at ND but not AD, its SL is partially trusted and the student also takes its own SL into account; (c) otherwise, the student only relies on its own SL. Experiments demonstrate the effectiveness of IAD for improving upon teachers in terms of adversarial robustness.

cs.LG↗

arXiv2022

Direct observation of local antiferroelectricity induced phonon softening at a SrTiO3 defect

Defects in oxides usually exhibit exotic properties that may be associated with the local lattice dynamics. Here, at atomic spatial resolution, we directly measure phonon modes of an antiphase boundary (APB) in SrTiO3 freestanding membrane and correlate them with the picometer-level structural distortion. We find that the SrTiO3 APB introduces new defect phonon modes that are absent in bulk SrTiO3. These modes are highly sensitive to the subtle structure distortion, i.e., the SrTiO3 APB generates the local electric dipoles forming an antiferroelectric configuration, which significantly softens the transverse optical (TO) and longitudinal optical (LO) modes at Γ point. Correlating the local phonons with the subtle structural distortion, our findings provide valuable insights into understanding the defect properties in complex oxides and essential information for their applications such as thermoelectric devices.

cond-mat.mtrl-sci↗

arXiv2022

Do We Need to Penalize Variance of Losses for Learning with Label Noise?

Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels. Intuitively, when there is a finite training sample, penalizing the variance of losses will improve the stability and generalization of the algorithms. Interestingly, we found that the variance should be increased for the problem of learning with noisy labels. Specifically, increasing the variance will boost the memorization effects and reduce the harmfulness of incorrect labels. By exploiting the label noise transition matrix, regularizers can be easily designed to reduce the variance of losses and be plugged in many existing algorithms. Empirically, the proposed method by increasing the variance of losses significantly improves the generalization ability of baselines on both synthetic and real-world datasets.

cs.LG↗

arXiv2022

From the synthesis of hBN crystals to their use as nanosheets for optoelectronic devices

In the wide world of 2D materials, hexagonal boron nitride (hBN) holds a special place due to its excellent characteristics. In addition to its thermal, chemical and mechanical stability, hBN demonstrates high thermal conductivity, low compressibility, and wide band gap around 6 eV, making it promising candidate for many groundbreaking applications and more specifically for optoelectronic devices. Millimeters scale hexagonal boron nitride crystals are obtained through a disruptive dual method (PDC/PCS) consisting in a complementary coupling of the Polymer Derived Ceramics route and a Pressure-Controlled Sintering process. In addition to their excellent chemical and crystalline quality, these crystals exhibit a free exciton lifetime of 0.43 ns, as determined by time-resolved cathodoluminescence measurements, confirming their interesting optical properties. To go further in applicative fields, hBN crystals are then exfoliated, and resulting Boron Nitride NanoSheets (BNNSs) are used to encapsulate transition metal dichalcogenides (TMDs). Such van der Waals heterostructures are tested by optical spectroscopy. BNNSs do not luminesce in the emission spectral range of TMDs and the photoluminescence width of the exciton at 4K is in the range 2-3 meV. All these results demonstrate that these BNNSs are relevant for future opto-electronic applications.

cond-mat.mtrl-sci↗

arXiv2022

Nebula: Reliable Low-latency Video Transmission for Mobile Cloud Gaming

Mobile cloud gaming enables high-end games on constrained devices by streaming the game content from powerful servers through mobile networks. Mobile networks suffer from highly variable bandwidth, latency, and losses that affect the gaming experience. This paper introduces Nebula, an end-to-end cloud gaming framework to minimize the impact of network conditions on the user experience. Nebula relies on an end-to-end distortion model adapting the video source rate and the amount of frame-level redundancy based on the measured network conditions. As a result, it minimizes the motion-to-photon (MTP) latency while protecting the frames from losses. We fully implement Nebula and evaluate its performance against the state of the art techniques and latest research in real-time mobile cloud gaming transmission on a physical testbed over emulated and real wireless networks. Nebula consistently balances MTP latency (<140 ms) and visual quality (>31 dB) even in highly variable environments. A user experiment confirms that Nebula maximizes the user experience with high perceived video quality, playability, and low user load.

cs.MM↗

arXiv2022

Pointwise Binary Classification with Pairwise Confidence Comparisons

To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed. Among them, some consider using pairwise but not pointwise labels, when pointwise labels are not accessible due to privacy, confidentiality, or security reasons. However, as a pairwise label denotes whether or not two data points share a pointwise label, it cannot be easily collected if either point is equally likely to be positive or negative. Thus, in this paper, we propose a novel setting called pairwise comparison (Pcomp) classification, where we have only pairs of unlabeled data that we know one is more likely to be positive than the other. Firstly, we give a Pcomp data generation process, derive an unbiased risk estimator (URE) with theoretical guarantee, and further improve URE using correction functions. Secondly, we link Pcomp classification to noisy-label learning to develop a progressive URE and improve it by imposing consistency regularization. Finally, we demonstrate by experiments the effectiveness of our methods, which suggests Pcomp is a valuable and practically useful type of pairwise supervision besides the pairwise label.

cs.LG↗

arXiv2021

Understanding and Improving Early Stopping for Learning with Noisy Labels

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of training, is usually adopted. Current methods generally decide the early stopping point by considering a DNN as a whole. However, a DNN can be considered as a composition of a series of layers, and we find that the latter layers in a DNN are much more sensitive to label noise, while their former counterparts are quite robust. Therefore, selecting a stopping point for the whole network may make different DNN layers antagonistically affected each other, thus degrading the final performance. In this paper, we propose to separate a DNN into different parts and progressively train them to address this problem. Instead of the early stopping, which trains a whole DNN all at once, we initially train former DNN layers by optimizing the DNN with a relatively large number of epochs. During training, we progressively train the latter DNN layers by using a smaller number of epochs with the preceding layers fixed to counteract the impact of noisy labels. We term the proposed method as progressive early stopping (PES). Despite its simplicity, compared with the early stopping, PES can help to obtain more promising and stable results. Furthermore, by combining PES with existing approaches on noisy label training, we achieve state-of-the-art performance on image classification benchmarks.

cs.LG↗

arXiv2021

Riemann-Hilbert problem of the three-component coupled Sasa-Satsuma equation and its multi-soliton solutions

In this work, the inverse scattering transform of the three-component coupled Sasa-Satsuma equation is investigated via the Riemann-Hilbert method. Firstly we consider a Lax pair associated with a $7\times 7$ matrix spectral problem for the equation. Then we present the spectral analysis of the Lax pair, from which a kind of Riemann-Hilbert problem is formulated. Moreover, $N$-soliton solutions to the equation are constructed through a particular Riemann-Hilbert problem with vanishing scattering coefficients. Finally, the dynamics of the soliton solutions are discussed with some graphics.

math.AP↗