检索结果-内蒙古大学图书馆

big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (big-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/big-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

Multifunctional optical thermometry based on La2MgSnO6:Mn4+, M (M=Bi3+, Sm3+) double perovskite phosphors

学校读者我要写书评

暂无评论

Physica B: Condensed Matter 2025年 711卷

作者： Ma, Rongbo Gong, Xinyong Deng, Chaoyong Huang, Weichao Key Laboratory of Functional Composite Materials of Guizhou Province College of Big Data and Information Engineering Guizhou University Guizhou Guiyang550025 China School of Electronics and Information Engineering Guiyang University Guizhou Guiyang550005 China

To develop novel luminescent materials for optical thermometry, a series of La2MgSnO6:Mn4+, M (M = Bi3+, Sm3+) phosphors were prepared by the solid-state method. Upon UV excitation, the La2MgSnO6: Mn4+ sample demonstrates strong red emission originating from the 2Eg → 4A2g transition of Mn4+. By co-doping with Bi3+ or Sm3+, it becomes possible to achieve tunable emission in La2MgSnO6 phosphors. Due to the different thermal quenching behavior between the Mn4+ and Bi3+ or Sm3+, a high-sensitivity thermometric was developed using the fluorescence intensity ratio mode. The maximum sensitivity was obtained to 1.5 %K−1 at 473K. The emission spectra of La2MgSnO6: Mn4+, M (M = Bi3+, Sm3+) phosphor significantly coincide with the absorption spectra of plant pigments in the blue and red regions. These findings indicate that the as-prepared La2MgSnO6: Mn4+, M (M = Bi3+, Sm3+) phosphors are promising candidate materials for plant cultivation and high-temperature optical thermometry. © 2025 Elsevier B.V.

关键词： Perovskite

LLMIdxAdvis: Resource-Efficient Index Advisor Utilizing Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Xinxin Li, Haoyang Zhang, Jing Huang, Xinmei Zhang, Tieying Chen, Jianjun Shi, Rui Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China ByteDance China

Index recommendation is essential for improving query performance in database management systems (DBMSs) through creating an optimal set of indexes under specific constraints. Traditional methods, such as heuristic and learning-based approaches, are effective but face challenges like lengthy recommendation time, resource-intensive training, and poor generalization across different workloads and database schemas. To address these issues, we propose LLMIdxAdvis, a resource-efficient index advisor that uses large language models (LLMs) without extensive fine-tuning. LLMIdxAdvis frames index recommendation as a sequence-to-sequence task, taking target workload, storage constraint, and corresponding database environment as input, and directly outputting recommended indexes. It constructs a high-quality demonstration pool offline, using GPT-4-Turbo to synthesize diverse SQL queries and applying integrated heuristic methods to collect both default and refined labels. During recommendation, these demonstrations are ranked to inject database expertise via in-context learning. Additionally, LLMIdxAdvis extracts workload features involving specific column statistical information to strengthen LLM’s understanding, and introduces a novel inference scaling strategy combining vertical scaling (via "Index-Guided Major Voting" and Best-of-N) and horizontal scaling (through iterative "self-optimization" with database feedback) to enhance reliability. Experiments on 3 OLAP and 2 real-world benchmarks reveal that LLMIdxAdvis delivers competitive index recommendation with reduced runtime, and generalizes effectively across different workloads and database schemas. Copyright © 2025, The Authors. All rights reserved.

关键词： Query languages

Mining User–Item Interactions via knowledge Graph for Recommendation

学校读者我要写书评

暂无评论

ACM Transactions on Recommender Systems 2025年第3期3卷 1-19页

作者： Shenghao Liu Lingyun Lu Bang Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology (HUST) Wuhan China

Introducing a knowledge Graph (KG) to facilitate a recommender system has become a tendency in recent years. Many existing methods leverage KGs to obtain side information of items to promote item representation learning for enhancing recommendation performance. However, they ignore that KGs also may contribute to better user representation learning. To solve this issue, we propose a novel algorithm, the KIGR (knowledge-aware Interaction Graph for Recommendation), to mine user–item interactions via KGs for assisting user representation learning. Specifically, a user–item interaction is encoded by attentively summing up the relation embedding about the item in the KG. Then, an unsupervised learning method is used to group the user–item interactions into different latent types. Further, a user–item interaction graph is divided into several subgraphs, which is referred to as a knowledge-aware Interaction Graph, making each subgraph only contain one latent type of interaction. Finally, user representation is the fusion of user interest embedding, which is learned on the knowledge-aware interaction graph, whereas item representation is learned on the KG. Experimental results on MovieLens, LastFM and Amazon-Book validate that the proposed KIGR has a superior performance compared with the state-of-the-art algorithms.

关键词： Recommendation system knowledge graph graph neural network

Learning with Open-world Noisy data via Class-independent Margin in Dual Representation Space

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source...

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Dong, Jinwei Wang, Xinsheng Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350368741

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method's superior performance over existing diffusion and discriminative models, validating its efficacy. © 2025 IEEE.

关键词： diffusion score matching speech separation stochastic differential equation

Efficient Modeling Attack on Multiplexer PUFs via Kronecker Matrix Multiplication

学校读者我要写书评

暂无评论

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Wang, Hongfei Wan, Caixue Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China

The Physical Unclonable Function (PUF) is valued for its lightweight nature and unique functionality, making it a common choice for securing hardware products requiring authentication and key generation mechanisms. In response to the susceptibility of individual PUFs to modeling attacks, advanced PUF variants have been developed to improve security measures. One notable type in this regard is the multiplexer-based composition of arbiter PUFs, known as MPUF, which aims to meet high reliability and security standards simultaneously. Current research on attacking MPUF encounters challenges such as substantial demands for training CRPs and low success rates. In this work, we propose a novel numerical modeling attack strategy for MPUFs. Using Kronecker products from mathematical perspective, this method precisely describe the MPUF model without using complex network architectures, boosting attack accuracy and overall efficiency. Experiment comparison with state-of-the-art works demonstrates that our method achieves better performance in terms of attack accuracy, robustness, and efficiency. Our method is able to successfully attack a (512, 8)-MPUF in 32.71 minutes with 97.14% accuracy, outperforming all existing attack methods on MPUFs. More, we validate our method through experiments with hardware implementations on FPGAs. The advantages of our method also include the adaptability to be employed to attack other MPUF variations like cMPUF and rMPUF, and the capability to be integrated with an existing attack method for launching efficient attack on MPUFs leveraging reliability information. © 2025 IEEE.

关键词： modeling attack multiplexer-based PUF Physical unclonable function

Out-of-Distribution Generalization on Graphs via Progressive Inference

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xu, Yiming Shi, Bin Peng, Zhen Liu, Huixiang Dong, Bo Chen, Chen School of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Distance Education Xi’an Jiaotong University China University of Virginia CharlottesvilleVA United States

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%. 1 © 2025, CC BY.

关键词： Graph neural networks

Compressing Model with Few Class-Imbalance Samples: An Out-of-Distribution Expedition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Tian-Shuang Lyu, Shen-Huan Chen, Ning Qu, Zhihao Ye, Baoliu Key Laboratory of Water Big Data Technology Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

In recent years, as a compromise between privacy and performance, few-sample model compression has been widely adopted to deal with limited data resulting from privacy and security concerns. However, when the number of available samples is extremely limited, class imbalance becomes a common and tricky problem. Achieving an equal number of samples across all classes is often costly and impractical in real-world applications, and previous studies on few-sample model compression have mostly ignored this significant issue. Our experiments comprehensively demonstrate that class imbalance negatively affects the overall performance of few-sample model compression methods. To address this problem, we propose a novel and adaptive framework named OOD-Enhanced Few-Sample Model Compression (OE-FSMC). This framework integrates easily accessible out-of-distribution (OOD) data into both the compression and fine-tuning processes, effectively rebalancing the training distribution. We also incorporate a joint distillation loss and a regularization term to reduce the risk of the model overfitting to the OOD data. Extensive experiments on multiple benchmark datasets show that our framework can be seamlessly incorporated into existing few-sample model compression methods, effectively mitigating the accuracy degradation caused by class imbalance. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy