检索结果-内蒙古大学图书馆

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

学校读者我要写书评

暂无评论

IEEE Transactions on Affective Computing 2024年第2期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

Counterfactual Faithful data Generation Based on Disentangled Representation for Compound Fault Diagnosis of Rolling Bearings

学校读者我要写书评

暂无评论

Counterfactual Faithful Data Generation Based on Disentangle...

Sensing, Measurement & data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Xu Ding Qiang Zhu Song Wang Yiqi Zhang Hui Wang Juan Xu Institute of Industry and Equipment Technology Hefei University of Technology Hefei China School of Mechanical Engineering Hefei University of Technology Hefei China Bengbu Triumph Engineering Technology Co. Ltd Bengbu China Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology Hefei China

Recently, deep learning and human-out-of-the-loop methods enjoy their prosperous applications in mechanical fault diagnosis. Nonetheless, the None-IID(independent and identically distributed) issue radicated in acquired data severely limits the stability and accuracy of compound fault diagnosis of rolling bearings. This paper proposes a sample augmentation method for generating simulated signals based on the concept of counterfactuals. Firstly, disentangled representations and counterfactual faithful theory are applied to classify the original signal into two categories of properties. One is the fault semantics encoded from the original vibration signal. And the other is the sample attribute encoded by the encoder of Variational Autoencoders (VAEs). Secondly, the counterfactual faithful pseudo-samples are conjured through the Generative Adversarial Network(GAN) using the seeds of the “factual” sample attributes and “counterfactual” fault semantics to compensate for the drawback of distribution shift. Finally, the original samples and pseudo-samples are used as the CNN classifier dataset to realize bearing fault diagnosis. Experiments show that this method can generate counterfactual signals that are highly consistent with the original data distribution and can achieve better classification accuracy after balancing the dataset.

关键词： Fault diagnosis Wavelet transforms Vibrations Semantics Rolling bearings Feature extraction Stability analysis

Computationally Efficient Approximations for Matrix-based Rényi's Entropy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gong, Tieliang Dong, Yuxin Yu, Shujian Dong, Bo The School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an710049 China The Machine Learning Group UiT - The Arctic University of Norway Department of Computer Science Vrije University Amsterdam Amsterdam Netherlands

The recently developed matrix-based Rényi's αorder entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi-definite (PSD) matrices in reproducing kernel Hilbert space, without estimation of the underlying data distribution. This intriguing property makes this new information measurement widely adopted in multiple statistical inference and learning tasks. However, the computation of such quantity involves the trace operator on a PSD matrix G to power α (i.e., tr(Gα)), with a normal complexity of nearly O(n3), which severely hampers its practical usage when the number of samples (i.e., n) is large. In this work, we present computationally efficient approximations to this new entropy functional that can reduce its complexity to even significantly less than O(n2). To this end, we leverage the recent progress on Randomized Numerical Linear Algebra, developing Taylor, Chebyshev and Lanczos approximations to tr(Gα) for arbitrary values of α by converting it into a matrix-vector multiplication problem. We also establish the connection between the matrix-based Rényi's entropy and PSD matrix approximation, which enables exploiting both clustering and block low-rank structure of G to further reduce the computational cost. We theoretically provide approximation accuracy guarantees and illustrate the properties for different approximations. Large-scale experimental evaluations on both synthetic and real-world data corroborate our theoretical findings, showing promising speedup with negligible loss in accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Matrix algebra

Dynamic Tracking with Fuzzy Rules for Evolutionary Dynamic Constrained Optimization

学校读者我要写书评

暂无评论

Dynamic Tracking with Fuzzy Rules for Evolutionary Dynamic C...

IEEE International Conference on Systems, Man and Cybernetics

作者： Chenyang Bu Yuxin Liu Lizhong Zhang Tao Zhu Wenjian Luo Ministry of Education Key Laboratory of Knowledge Engineering with Big Data School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China School of Computer Science and Information Engineering University of South China Hengyang Hunan China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Guangdong China

Nature-inspired population-based stochastic search algorithms (SSA) have demonstrated effectiveness in solving many real-world dynamic optimization problems (DOPs), such as dynamic optimal power flow (DOPF) problems. The basic idea of solving DOPs using SSAs is to “track the moving optima”, rather than solving the changed problems from scratch. Its hidden assumption is that the problems are slightly changed in general, and it is expected that the search process can be accelerated by learning from past search experiences. However, the hidden assumption that the current search process can always benefit from previous search experiences might not be true for certain cases. For example, if the current problem is not similar to any of its previous problems, the historical solutions might not be helpful for the current search. To reduce such negative transfer, the following issues are worthy of study: how to choose which historical problems to learn from, and how to determine the degree of learning from historical problems. To solve the above problems, we propose a dynamic processing framework based on fuzzy rules from the perspective of incorporating human knowledge for optima tracking. The experimental results on the DOPF problems show that the SSA with the proposed optima tracking strategy outperforms other comparative algorithms. We open up the code and data of our algorithm 4 4 https://***/DMiC-Lab-HFUT/SMDE-Transfer.

关键词：

Human-in-The-Loop Optimization for Vehicle Body Lightweight Design

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Hao, Jia Deng, Ruofan Jia, Liangyue Li, Zuoxuan Industrial and Systems Engineering Laboratory Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314019 China Key Laboratory of Industry Knowledge & Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China

Automatic optimization algorithms play an important role in vehicle body lightweight design;however, the existing methods are still inefficient and result in excessive iterations that escalate both time and costs. Current interactive optimization strategies partially mitigate this issue but fall short in offering a broad spectrum of manipulation points and auxiliary information model, essential for optimizing design efficiency and accuracy. As such, we introduce a novel approach, "Human-in-the-Loop based method for Vehicle Body Lightweight Design" (HIL-VBLD). This method seamlessly integrates human decision-making with optimization algorithms to reduce unproductive iterations. HIL-VBLD comprises two key components: (1) a novel interaction mode offering multiple manipulation points including constraint modification, algorithm switching, and selection of solutions of interest (SOI);(2) A comprehensive auxiliary information model aids in decision-making for designers. Our analysis underscores HIL-VBLD's efficacy, evidenced by a 54.5% reduction in iteration cycles for genetic algorithm using SOI selection. Algorithm switching led to a 4.5% mass reduction, circumventing local optimum pitfalls associated with gradient algorithms. Additionally, the auxiliary information model contributed to a further 1.25% mass reduction, enhancing optimization robustness. Compared to conventional automatic algorithm switching strategies, HIL-VBLD maintains equivalent accuracy with 23.9% fewer iterations. © 2024, The Authors. All rights reserved.

关键词： Genetic algorithms

Multi-frame joint enhancement for early interlaced videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Yang Ma, Yanbo Chen, Yuan Jia, Wei Wang, Ronggang Liu, Xiaoping The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei230009 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School 2199 Lishui Road Shenzhen518055 China Peng Cheng Laboratory Shenzhen518000 China

Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in real-world early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos. Copyright © 2021, The Authors. All rights reserved.

关键词： Image reconstruction

ER: Equivariance Regularizer for knowledge Graph Completion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Tensor factorization and distanced based models play important roles in knowledge graph completion (KGC). However, the relational matrices in KGC methods often induce a high model complexity, bearing a high risk of overfitting. As a remedy, researchers propose a variety of different regularizers such as the tensor nuclear norm regularizer. Our motivation is based on the observation that the previous work only focuses on the "size" of the parametric space, while leaving the implicit semantic information widely untouched. To address this issue, we propose a new regularizer, namely, Equivariance Regularizer (ER), which can suppress overfitting by leveraging the implicit semantic information. Specifically, ER can enhance the generalization ability of the model by employing the semantic equivariance between the head and tail entities. Moreover, it is a generic solution for both distance based models and tensor factorization based models. The experimental results indicate a clear and substantial improvement over the state-of-the-art relation prediction methods. © 2022, CC BY.

关键词： knowledge graph

Geometry Interaction knowledge Graph Embeddings

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks. Previous work usually embeds KGs into a single geometric space such as Euclidean space (zero curved), hyperbolic space (negatively curved) or hyperspherical space (positively curved) to maintain their specific geometric structures (e.g., chain, hierarchy and ring structures). However, the topological structure of KGs appears to be complicated, since it may contain multiple types of geometric structures simultaneously. Therefore, embedding KGs in a single space, no matter the Euclidean space, hyperbolic space or hyperspheric space, cannot capture the complex structures of KGs accurately. To overcome this challenge, we propose Geometry Interaction knowledge graph Embeddings (GIE), which learns spatial structures interactively between the Euclidean, hyperbolic and hyperspherical spaces. Theoretically, our proposed GIE can capture a richer set of relational information, model key inference patterns, and enable expressive semantic matching across entities. Experimental results on three well-established knowledge graph completion benchmarks show that our GIE achieves the state-of-the-art performance with fewer parameters. © 2022, CC BY.

关键词： knowledge graph

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning