arXiv subjects

Cong Wang

Publications and source records attributed to Cong Wang.

At least 289 records · Page 16Linked to original sources

arXiv2023

Frame-level emotional state alignment method for speech emotion recognition

Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective states consistent with utterance-level label, which makes it difficult for the model to distinguish the true emotion of the audio and perform poorly. To address this problem, we propose a frame-level emotional state alignment method for SER. First, we fine-tune HuBERT model to obtain a SER system with task-adaptive pretraining (TAPT) method, and extract embeddings from its transformer layers to form frame-level pseudo-emotion labels with clustering. Then, the pseudo labels are used to pretrain HuBERT. Hence, the each frame output of HuBERT has corresponding emotional information. Finally, we fine-tune the above pretrained HuBERT for SER by adding an attention layer on the top of it, which can focus only on those frames that are emotionally more consistent with utterance-level label. The experimental results performed on IEMOCAP indicate that our proposed method performs better than state-of-the-art (SOTA) methods.

cs.SD↗

arXiv2023

Detection and Mitigation of Position Spoofing Attacks on Cooperative UAV Swarm Formations

Detecting spoofing attacks on the positions of unmanned aerial vehicles (UAVs) within a swarm is challenging. Traditional methods relying solely on individually reported positions and pairwise distance measurements are ineffective in identifying the misbehavior of malicious UAVs. This paper presents a novel systematic structure designed to detect and mitigate spoofing attacks in UAV swarms. We formulate the problem of detecting malicious UAVs as a localization feasibility problem, leveraging the reported positions and distance measurements. To address this problem, we develop a semidefinite relaxation (SDR) approach, which reformulates the non-convex localization problem into a convex and tractable semidefinite program (SDP). Additionally, we propose two innovative algorithms that leverage the proximity of neighboring UAVs to identify malicious UAVs effectively. Simulations demonstrate the superior performance of our proposed approaches compared to existing benchmarks. Our methods exhibit robustness across various swarm networks, showcasing their effectiveness in detecting and mitigating spoofing attacks. {\blue Specifically, the detection success rate is improved by up to 65\%, 55\%, and 51\% against distributed, collusion, and mixed attacks, respectively, compared to the benchmarks.

eess.SY↗

arXiv2023

Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Process

Diffusion models have rapidly become a vital part of deep generative architectures, given today's increasing demands. Obtaining large, high-performance diffusion models demands significant resources, highlighting their importance as intellectual property worth protecting. However, existing watermarking techniques for ownership verification are insufficient when applied to diffusion models. Very recent research in watermarking diffusion models either exposes watermarks during task generation, which harms the imperceptibility, or is developed for conditional diffusion models that require prompts to trigger the watermark. This paper introduces WDM, a novel watermarking solution for diffusion models without imprinting the watermark during task generation. It involves training a model to concurrently learn a Watermark Diffusion Process (WDP) for embedding watermarks alongside the standard diffusion process for task generation. We provide a detailed theoretical analysis of WDP training and sampling, relating it to a shifted Gaussian diffusion process via the same reverse noise. Extensive experiments are conducted to validate the effectiveness and robustness of our approach in various trigger and watermark data configurations.

cs.CR↗

arXiv2023

Augmenting x-ray single particle imaging reconstruction with self-supervised machine learning

The development of X-ray Free Electron Lasers (XFELs) has opened numerous opportunities to probe atomic structure and ultrafast dynamics of various materials. Single Particle Imaging (SPI) with XFELs enables the investigation of biological particles in their natural physiological states with unparalleled temporal resolution, while circumventing the need for cryogenic conditions or crystallization. However, reconstructing real-space structures from reciprocal-space x-ray diffraction data is highly challenging due to the absence of phase and orientation information, which is further complicated by weak scattering signals and considerable fluctuations in the number of photons per pulse. In this work, we present an end-to-end, self-supervised machine learning approach to recover particle orientations and estimate reciprocal space intensities from diffraction images only. Our method demonstrates great robustness under demanding experimental conditions with significantly enhanced reconstruction capabilities compared with conventional algorithms, and signifies a paradigm shift in SPI as currently practiced at XFELs.

cs.CV↗

arXiv2023

DualMatch: Robust Semi-Supervised Learning with Dual-Level Interaction

Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match model predictions of different data-augmented views in a single-level interaction manner, which highly relies on the quality of pseudo-labels and results in semi-supervised learning not robust. In this paper, we propose a novel SSL method called DualMatch, in which the class prediction jointly invokes feature embedding in a dual-level interaction manner. DualMatch requires consistent regularizations for data augmentation, specifically, 1) ensuring that different augmented views are regulated with consistent class predictions, and 2) ensuring that different data of one class are regulated with similar feature embeddings. Extensive experiments demonstrate the effectiveness of DualMatch. In the standard SSL setting, the proposal achieves 9% error reduction compared with SOTA methods, even in a more challenging class-imbalanced setting, the proposal can still achieve 6% error reduction. Code is available at https://github.com/CWangAI/DualMatch

cs.CV↗

arXiv2023

Adaptive Gating in Mixture-of-Experts based Language Models

Large language models, such as OpenAI's ChatGPT, have demonstrated exceptional language understanding capabilities in various NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models while maintaining a constant number of computational operations. Existing MoE model adopts a fixed gating network where each token is computed by the same number of experts. However, this approach contradicts our intuition that the tokens in each sequence vary in terms of their linguistic complexity and, consequently, require different computational costs. Little is discussed in prior research on the trade-off between computation per token and model performance. This paper introduces adaptive gating in MoE, a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution. The proposed framework preserves sparsity while improving training efficiency. Additionally, curriculum learning is leveraged to further reduce training time. Extensive experiments on diverse NLP tasks show that adaptive gating reduces at most 22.5% training time while maintaining inference quality. Moreover, we conduct a comprehensive analysis of the routing decisions and present our insights when adaptive gating is used.

cs.CL↗

arXiv2023

Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration

Recent years have witnessed the remarkable performance of diffusion models in various vision tasks. However, for image restoration that aims to recover clear images with sharper details from given degraded observations, diffusion-based methods may fail to recover promising results due to inaccurate noise estimation. Moreover, simple constraining noises cannot effectively learn complex degradation information, which subsequently hinders the model capacity. To solve the above problems, we propose a coarse-to-fine diffusion Transformer (C2F-DFT) for image restoration. Specifically, our C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) within a new coarse-to-fine training scheme. The DFSA and DFN respectively capture the long-range diffusion dependencies and learn hierarchy diffusion representation to facilitate better restoration. In the coarse training stage, our C2F-DFT estimates noises and then generates the final clean image by a sampling algorithm. To further improve the restoration quality, we propose a simple yet effective fine training scheme. It first exploits the coarse-trained diffusion model with fixed steps to generate restoration results, which then would be constrained with corresponding ground-truth ones to optimize the models to remedy the unsatisfactory results affected by inaccurate noise estimation. Extensive experiments show that C2F-DFT significantly outperforms diffusion-based restoration method IR-SDE and achieves competitive performance compared with Transformer-based state-of-the-art methods on $3$ tasks, including image deraining, image deblurring, and real image denoising. Code is available at https://github.com/wlydlut/C2F-DFT.

cs.CV↗

arXiv2023

Self-supervised Learning for Anomaly Detection in Computational Workflows

Anomaly detection is the task of identifying abnormal behavior of a system. Anomaly detection in computational workflows is of special interest because of its wide implications in various domains such as cybersecurity, finance, and social networks. However, anomaly detection in computational workflows~(often modeled as graphs) is a relatively unexplored problem and poses distinct challenges. For instance, when anomaly detection is performed on graph data, the complex interdependency of nodes and edges, the heterogeneity of node attributes, and edge types must be accounted for. Although the use of graph neural networks can help capture complex inter-dependencies, the scarcity of labeled anomalous examples from workflow executions is still a significant challenge. To address this problem, we introduce an autoencoder-driven self-supervised learning~(SSL) approach that learns a summary statistic from unlabeled workflow data and estimates the normal behavior of the computational workflow in the latent space. In this approach, we combine generative and contrastive learning objectives to detect outliers in the summary statistics. We demonstrate that by estimating the distribution of normal behavior in the latent space, we can outperform state-of-the-art anomaly detection methods on our benchmark datasets.

cs.LG↗

arXiv2023

Parallel in-memory wireless computing

Parallel wireless digital communication with ultralow power consumption is critical for emerging edge technologies such as 5G and Internet of Things. However, the physical separation between digital computing units and analogue transmission units in traditional wireless technology leads to high power consumption. Here we report a parallel in-memory wireless computing scheme. The approach combines in-memory computing with wireless communication using memristive crossbar arrays. We show that the system can be used for the radio transmission of a binary stream of 480 bits with a bit error rate of 0. The in-memory wireless computing uses two orders of magnitude less power than conventional technology (based on digital-to-analogue and analogue-to-digital converters). We also show that the approach can be applied to acoustic and optical wireless communications

cs.AR↗

arXiv2023

Vernier Microcombs for Integrated Optical Atomic Clocks

CMOS-compatible Kerr microcombs have drawn substantial interest as mass-manufacturable, compact alternatives to bulk frequency combs. This could enable deployment of many comb-reliant applications previously confined to laboratories. Particularly enticing is the prospect of microcombs performing optical frequency division in compact optical atomic clocks. Unfortunately, it is difficult to meet the self-referencing requirement of microcombs in these systems due to the $\sim$THz repetition rates typically required for octave-spanning comb generation. Additionally, it is challenging to spectrally engineer a microcomb system to align a comb mode with an atomic clock transition with sufficient signal-to-noise ratio. Here, we adopt a Vernier dual-microcomb scheme for optical frequency division of a stabilized ultranarrow-linewidth continuous-wave laser at 871 nm to a $\sim$235 MHz output frequency. In addition to enabling measurement of the comb repetition rates, this scheme brings the freedom to pick comb lines from either or both of the combs. We exploit this flexibility to shift an ultra-high-frequency ($\sim$100 GHz) carrier-envelope offset beat down to frequencies where detection is possible and to place a comb line close to the 871 nm laser - tuned so that if frequency-doubled it would fall close to the clock transition in $^{171}$Yb$^+$. Moreover, we introduce a novel scheme which suppresses frequency noise arising from interferometric phase fluctuations in our dual-comb system and reduces the frequency instability down to our measurement limit. Our dual-comb system can potentially combine with an integrated ion trap toward future chip-scale optical atomic clocks.

physics.optics↗

arXiv2023

Uniqueness of blowup at singular points for superconductivity problem

In this paper, we prove that the uniqueness of blowup at the maximum point of coincidence set of the superconductivity problem, mainly based on the Weiss-type and Monneau-type monotonicity formulas, and the proof of the main results in this paper is inspired the recent paper \cite{CFL22} by Chen-Feng-Li.

math.AP↗

arXiv2023

Leakage-Abuse Attacks Against Forward and Backward Private Searchable Symmetric Encryption

Dynamic searchable symmetric encryption (DSSE) enables a server to efficiently search and update over encrypted files. To minimize the leakage during updates, a security notion named forward and backward privacy is expected for newly proposed DSSE schemes. Those schemes are generally constructed in a way to break the linkability across search and update queries to a given keyword. However, it remains underexplored whether forward and backward private DSSE is resilient against practical leakage-abuse attacks (LAAs), where an attacker attempts to recover query keywords from the leakage passively collected during queries. In this paper, we aim to be the first to answer this question firmly through two non-trivial efforts. First, we revisit the spectrum of forward and backward private DSSE schemes over the past few years, and unveil some inherent constructional limitations in most schemes. Those limitations allow attackers to exploit query equality and establish a guaranteed linkage among different (refreshed) query tokens surjective to a candidate keyword. Second, we refine volumetric leakage profiles of updates and queries by associating each with a specific operation. By further exploiting update volume and query response volume, we demonstrate that all forward and backward private DSSE schemes can leak the same volumetric information (e.g., insertion volume, deletion volume) as those without such security guarantees. To testify our findings, we realize two generic LAAs, i.e., frequency matching attack and volumetric inference attack, and we evaluate them over various experimental settings in the dynamic context. Finally, we call for new efficient schemes to protect query equality and volumetric information across search and update queries.

cs.CR↗

arXiv2023

Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning

For deep ordinal classification, learning a well-structured feature space specific to ordinal classification is helpful to properly capture the ordinal nature among classes. Intuitively, when Euclidean distance metric is used, an ideal ordinal layout in feature space would be that the sample clusters are arranged in class order along a straight line in space. However, enforcing samples to conform to a specific layout in the feature space is a challenging problem. To address this problem, in this paper, we propose a novel Constrained Proxies Learning (CPL) method, which can learn a proxy for each ordinal class and then adjusts the global layout of classes by constraining these proxies. Specifically, we propose two kinds of strategies: hard layout constraint and soft layout constraint. The hard layout constraint is realized by directly controlling the generation of proxies to force them to be placed in a strict linear layout or semicircular layout (i.e., two instantiations of strict ordinal layout). The soft layout constraint is realized by constraining that the proxy layout should always produce unimodal proxy-to-proxies similarity distribution for each proxy (i.e., to be a relaxed ordinal layout). Experiments show that the proposed CPL method outperforms previous deep ordinal classification methods under the same setting of feature extractor.

cs.CV↗

arXiv2023

The quasilinear Schrödinger--Poisson system

This paper deals with the $(p,q)$--Schrödinger--Poisson system \begin{eqnarray*} \left \{\begin{array}{ll} \displaystyle -Δ_p u+|u|^{p-2}u+λϕ|u|^{s-2}u=|u|^{r-2}u,&\mathrm{in} \ \mathbb{R}^3,\\ \displaystyle -Δ_q ϕ= |u|^s, &\mathrm{in}\ \mathbb{R}^3,\\ \end{array} \right. \end{eqnarray*} where $1 0$ is a parameter. This quasilinear system is new and has never been considered in the literature. The uniqueness of solutions of the quasilinear Poisson equation is obtained via the Minty--Browder theorem. The variational framework of the quasilinear system is built and the nontrivial solutions of the system are obtained via the mountain pass theorem.

math.AP↗

arXiv2023

Room-Temperature Ferromagnetism in Fe-doped SnSe Bulk Single Crystalline Semiconductor

The quest for pragmatic room-temperature (RT) magnetic semiconductors (MSs) with a suitable bandgap constitutes one of the contemporary opportunities to be exploited. This may provide a materials platform for to bring new-generation ideal information device technologies into real-world applications where the otherwise conventionally separately utilized charge and spin are simultaneously exploited. Here we present RT ferromagnetism in an Fe-doped SnSe (Fe:SnSe) van der Waals (vdW) single crystalline ferromagnetic semiconductor (FMS) with a semiconducting bandgap of ~1.19 eV (comparable to those of Si and GaAs). The synthesized Fe:SnSe single crystals feature a dilute Fe content of less than 1.0 at%, a Curie temperature of ~310 K, a layered vdW structure identical to that of pristine SnSe, and the absence of in-gap defect states. The Fe:SnSe vdW diluted magnetic semiconductor (DMS) single crystals are grown using a simple temperature-gradient melt-growth process, in which the magnetic Fe atom doping is realized uniquely using FeI2 as the dopant precursor whose melting point is low with respect to crystal growth, and which in principle possesses industrially unlimited scalability. Our work adds a new member in the family of long-searching RT magnetic semiconductors, and may establish a generalized strategy for large-volume production of related DMSs.

cond-mat.mtrl-sci↗

arXiv2023

PeakNet: An Autonomous Bragg Peak Finder with Deep Neural Networks

Serial crystallography at X-ray free electron laser (XFEL) and synchrotron facilities has experienced tremendous progress in recent times enabling novel scientific investigations into macromolecular structures and molecular processes. However, these experiments generate a significant amount of data posing computational challenges in data reduction and real-time feedback. Bragg peak finding algorithm is used to identify useful images and also provide real-time feedback about hit-rate and resolution. Shot-to-shot intensity fluctuations and strong background scattering from buffer solution, injection nozzle and other shielding materials make this a time-consuming optimization problem. Here, we present PeakNet, an autonomous Bragg peak finder that utilizes deep neural networks. The development of this system 1) eliminates the need for manual algorithm parameter tuning, 2) reduces false-positive peaks by adjusting to shot-to-shot variations in strong background scattering in real-time, 3) eliminates the laborious task of manually creating bad pixel masks and the need to store these masks per event since these can be regenerated on demand. PeakNet also exhibits exceptional runtime efficiency, processing a 1920-by-1920 pixel image around 90 ms on an NVIDIA 1080 Ti GPU, with the potential for further enhancements through parallelized analysis or GPU stream processing. PeakNet is well-suited for expert-level real-time serial crystallography data analysis at high data rates.

physics.ins-det↗

arXiv2023

Phase transitions associated with magnetic-field induced topological orbital momenta in a non-collinear antiferromagnet

Resistivity measurements are widely exploited to uncover electronic excitations and phase transitions in metallic solids. While single crystals are preferably studied to explore crystalline anisotropies, these usually cancel out in polycrystalline materials. Here we show that in polycrystalline Mn3Zn0.5Ge0.5N with non-collinear antiferromagnetic order, changes in the diagonal and, rather unexpected, off-diagonal components of the resistivity tensor occur at low temperatures indicating subtle transitions between magnetic phases of different symmetry. This is supported by neutron scattering and explained within a phenomenological model which suggests that the phase transitions in magnetic field are associated with field induced topological orbital momenta. The fact that we observe transitions between spin phases in a polycrystal, where effects of crystalline anisotropy are cancelled suggests that they are only controlled by exchange interactions. The observation of an off-diagonal resistivity extends the possibilities for realising antiferromagnetic spintronics with polycrystalline materials.

cond-mat.mtrl-sci↗

arXiv2023

CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control

Intrinsic motivation is a promising exploration technique for solving reinforcement learning tasks with sparse or absent extrinsic rewards. There exist two technical challenges in implementing intrinsic motivation: 1) how to design a proper intrinsic objective to facilitate efficient exploration; and 2) how to combine the intrinsic objective with the extrinsic objective to help find better solutions. In the current literature, the intrinsic objectives are all designed in a task-agnostic manner and combined with the extrinsic objective via simple addition (or used by itself for reward-free pre-training). In this work, we show that these designs would fail in typical sparse-reward continuous control tasks. To address the problem, we propose Constrained Intrinsic Motivation (CIM) to leverage readily attainable task priors to construct a constrained intrinsic objective, and at the same time, exploit the Lagrangian method to adaptively balance the intrinsic and extrinsic objectives via a simultaneous-maximization framework. We empirically show, on multiple sparse-reward continuous control tasks, that our CIM approach achieves greatly improved performance and sample efficiency over state-of-the-art methods. Moreover, the key techniques of our CIM can also be plugged into existing methods to boost their performances.

cs.LG↗