检索结果-内蒙古大学图书馆

Optg: Optimizing Gradient-Driven Criteria in Network Sparsity

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhang, Yuxin Lin, Mingbao Chen, Mengzhao Chao, Fei Tian, Yonghong Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Tecent Youtu Lab China Department of Computer Science and Technology Peking University China Peng Cheng Laboratory China Department of Artificial Intelligence School of Informatics Xiamen University China

Network sparsity receives popularity mostly due to its capability to reduce the complexity of the network. Extensive studies excavate gradient-driven sparsity. Typically, these methods are constructed upon the premise of weight independence, which however, is contrary to the fact that weights are mutually influenced. Thus, their performance remains to be improved. In this paper, we propose to optimize gradient-driven sparsity (OptG) by solving this independence paradox. Our motive comes from the recent advances in supermask training which shows that high-performing sparse subnetworks can be located by simply updating mask values without modifying any weight. We prove that supermask training is to accumulate the criteria of gradientdriven sparsity for both removed and preserved weights, and it can partly solve the independence paradox. Consequently, OptG integrates supermask training into gradient-driven sparsity, and a novel supermask optimizer is further proposed to comprehensively mitigate the independence paradox. Experiments show that OptG can well surpass many existing state-of-the-art competitors, especially at ultra-high sparsity levels. Our project is available at \url{https://***/zyxxmu/OptG}. © 2024, The Authors. All rights reserved.

关键词： Image classification

Federated Graph Learning for Cross-Domain Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Ziqi Peng, Zhaopeng Wang, Zihui Qi, Jianzhong Chen, Chaochao Pan, Weike Wen, Chenglu Wang, Cheng Fan, Xiaoliang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computing and Information Systems The University of Melbourne Australia College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Cross-domain recommendation (CDR) offers a promising solution to the data sparsity problem by enabling knowledge transfer across source and target domains. However, many recent CDR models overlook crucial issues such as privacy as well as the risk of negative transfer (which negatively impact model performance), especially in multi-domain settings. To address these challenges, we propose FedGCDR, a novel federated graph learning framework that securely and effectively leverages positive knowledge from multiple source domains. First, we design a positive knowledge transfer module that ensures privacy during inter-domain knowledge transmission. This module employs differential privacy-based knowledge extraction combined with a feature mapping mechanism, transforming source domain embeddings from federated graph attention networks into reliable domain knowledge. Second, we design a knowledge activation module to filter out potential harmful or conflicting knowledge from source domains, addressing the issues of negative transfer. This module enhances target domain training by expanding the graph of the target domain to generate reliable domain attentions and fine-tunes the target model for improved negative knowledge filtering and more accurate predictions. We conduct extensive experiments on 16 popular domains of the Amazon dataset, demonstrating that FedGCDR significantly outperforms state-of-the-art methods. © 2024, CC BY.

关键词： Federated learning

Homogeneous Graph Extraction: An Approach to Learning Heterogeneous Graph Embedding

学校读者我要写书评

暂无评论

Homogeneous Graph Extraction: An Approach to Learning Hetero...

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

作者： Shihao Gao Xiaoyan Yu Yu Cai Xulong Zhang Jianzong Wang Taisong Jin Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Ping An Technology Co. Ltd. Shenzhen China School of Computer Science and Technology Beijing Institute of Technology China School of Informatics Xiamen University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Heterogeneous Graph Neural Networks (HGNNs) aim to embed rich structural and semantic information of heterogeneous graphs into low-dimensional node representations. While HGNNs extend the foundational work of homogeneous Graph Neural Networks, the methodology for effectively transforming heterogeneous graphs into homogeneous graphs and then learning node representations remains under-explored. In this paper, we propose a novel heterogeneous graph embedding method via the Homogeneous Graph Extraction strategy, termed HGE. Specifically, the proposed method ingeniously harnesses information clusters and metapaths to extract tailored homogeneous graphs from the complex heterogeneous graph. Subsequently, these distilled homogeneous graphs are fed into a weight-shared homogeneous graph encoder to obtain embeddings with diverse semantic information. Finally, we employ an attention mechanism, which adeptly fuses embeddings derived from distinct homogeneous graphs, resulting in the more expressive capability of the nodes. The effectiveness of the proposed architecture was demonstrated through experiments on three real heterogeneous graph datasets.

关键词： Representation learning Attention mechanisms Fuses Semantics Signal processing Graph neural networks Acoustics Data mining Speech processing

Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Shubin Wu, Qiong Zhou, Yiyi Chen, Weijie Zhang, Rongsheng Sun, Xiaoshuai Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China Institute of Artificial Intelligence Xiamen University 361005 China Fuxi AI Lab NetEase Inc. China

Pre-trained language models (PLMs) have played an increasing role in vision-language (VL) learning, but they usually require a deep multi-modal branch for VL reasoning, resulting in excessive computation and memory overhead. Recently, visual prompting is a feasible way to adapt PLMs to VL tasks, but we notice that the use of all visual tokens will greatly execrate the already high computation, and the token placement is also vital to performance. Based on these observations, we propose a novel transfer learning approach for PLMs in this paper, termed Dynamic Visual Prompting (DVP). Concretely, DVP first deploys a cross-attention module to obtain text-related and compact visual prompt tokens, thereby greatly reducing the input length of PLMs. To obtain the optimal placement, we also equip DVP with a reinforcement-learning based search algorithm, which can automatically merge DVP with PLMs for different VL tasks via a very short search process. In addition, we also combine DVP with the recently popular adapter approach to keep the most parameters of PLMs intact during adaption, which also help PLMs achieve a quick shift between single- and multi-modal tasks. We apply DVP to two representative PLMs, namely BERT and T5, and a recent large language model called LLaMA. Extensive experiments are conducted on a set of VL reasoning benchmarks including VQA2.0, GQA, SNLI-VE and ScienceQA. The experimental results not only show the merits of DVP in performance and efficiency, e.g. +2.28% accuracy and -80% FLOPs on VQA2.0, but also confirm its superiority in adapting pre-trained language models to VL tasks. Our code is anonymously released at https://***/hsb1357173526/ Dynamic Visual Prompting. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Hypergraph-Enhanced Multi-Granularity Stochastic Weight Completion in Sparse Road Networks

学校读者我要写书评

暂无评论

ACM Transactions on Knowledge Discovery from Data 2025年第3期19卷

作者： Han, Xiaolin Zhang, Yikun Ma, Chenhao Shang, Xuequn Cheng, Reynold Grubenmann, Tobias Li, Xiaodong Northwestern Polytechnical Universit China and Laboratory for Advanced Computing and Intelligence Engineering Wuxi Xi'an China Northwestern Polytechnical University Xi'an China The Chinese University of Hong Kong - Shenzhen Shenzhen China The University of Hong Kong Hong Kong Edinburgh Napier University Edinburgh United Kingdom Xiamen University China and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen China

Road network applications, such as navigation, incident detection, and Point-of-Interest (POI) recommendation, make extensive use of network edge weights (e.g., traveling times). Some of these weights can be missing, especially in a road network where traffic data may not be available for every road. In this article, we study the stochastic weight completion (SWC) problem, which computes the weight distributions of missing road edges. This is difficult, due to the intricate temporal and spatial correlations among neighboring edges. Besides, the road network can be sparse, i.e., there is a lack of traveling information in a large portion of the network. To tackle these challenges, we propose a multi-granularity framework for Region-Wise Graph Completion (RegGC). To learn coarse spatial correlations among distantly located roads, we construct a region-wise hypergraph neural architecture based on semantic region dependencies. For finer spatial correlations, we incorporate contextual road network properties (e.g., speed limits, lane counts, and road types). Moreover, it incorporates recent and periodic dimensions of road traffic. We evaluate RegGC against 10 existing methods on 3 real road network datasets. They show that RegGC is more effective and efficient than state-of-the-art solutions. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Semantic Segmentation

RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Ming Zhang, Yan Cai, Shuqiang Fan, Shuqi Lin, Xincheng Dai, Yudi Shen, Siqi Wen, Chenglu Xu, Lan Ma, Yuexin Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China National Institute for Data Science in Health and Medicine Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Shanghai Engineering Research Center of Intelligent Vision and Imaging ShanghaiTech University China

Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes. Most of the HPE datasets and methods primarily rely on RGB, LiDAR, or IMU data. However, solely using these modalities or a combination of them may not be adequate for HPE, particularly for complex and fast movements. For holistic human motion understanding, we present RELI11D, a high-quality multimodal human motion dataset involves LiDAR, IMU system, RGB camera, and Event camera. It records the motions of 10 actors performing 5 sports in 7 scenes, including 3.32 hours of synchronized LiDAR point clouds, IMU measurement data, RGB videos and Event steams. Through extensive experiments, we demonstrate that the RELI11D presents considerable challenges and opportunities as it contains many rapid and complex motions that require precise location. To address the challenge of integrating different modalities, we propose LEIR, a multimodal baseline that effectively utilizes LiDAR Point Cloud, Event stream, and RGB through our cross-attention fusion strategy. We show that LEIR exhibits promising results for rapid motions and daily motions and that utilizing the characteristics of multiple modalities can indeed improve HPE performance. Both the dataset and source code release publicly in http://***/reli11d/, fostering collaboration and enabling further exploration in this field. © 2024, CC BY.

关键词： Cameras

Circular Formation Control for Networked Dynamic Autonomous Underwater Vehicles: Estimator-Based Approaches

学校读者我要写书评

暂无评论

IEEE Transactions on Control of Network Systems 2025年

作者： Xie, Jingjing Lan, Weiyao Tong, Feng Yu, Xiao Xiamen University Department of Automation China Xiamen University College of Ocean and Earth Sciences The National and Local Joint Engineering Research Center for Navigation and Location Service Technology Xiamen361005 China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China The Institute of Artificial Intelligence Xiamen361005 China

This paper investigates the circular formation control problem of networked dynamic autonomous underwater vehicles (AUVs) in a directed network. The objective is to make dynamic AUVs encircle a given target with specific radius and velocity. The network topology among all AUVs is modeled by a directed graph containing a spanning tree, and the target is only known to one AUV. Estimator-based approaches with the backstepping technique are proposed for cases with or without communication. First, in communication-based networks, AUVs are allowed to transmit information via communication devices. A dynamic control law consisting of a distributed estimator is proposed. By analyzing with perturbed system method, the multi-vehicle system achieves global exponential stability instead of asymptotic stability. Second, in communication-denied networks, AUVs depend only on the relative measurements from the onboard sensors. A dynamic control law consisting of a decentralized estimator is proposed. By small-gain analysis, the global asymptotic stability for the multi-vehicle system is established. To demonstrate effectiveness, simulation results are presented. © 2014 IEEE.

关键词： Directed graphs

Interpretable Solutions for Multi-Physics PDEs Using T-NNGP 39

学校读者我要写书评

暂无评论

Interpretable Solutions for Multi-Physics PDEs Using T-NNGP

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cao, Lulu Lin, Zexin Tan, Kay Chen Jiang, Min Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Informatics Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen University China Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)157735897X

Multiphysics simulation aims to predict and understand interactions between multiple physical phenomena, aiding in comprehending natural processes and guiding engineering design. The system of Partial Differential Equations (PDEs) is crucial for representing these physical fields, and solving these PDEs is fundamental to such simulations. However, current methods primarily yield numerical outputs, limiting interpretability and generalizability. We introduce T-NNGP, a hybrid genetic programming algorithm that integrates traditional numerical methods with deep learning to derive approximate symbolic expressions for multiple unknown functions within a system of PDEs. T-NNGP initially obtains numerical solutions using traditional methods, then generates candidate symbolic expressions via deep reinforcement learning, and finally optimizes these expressions using genetic programming. Furthermore, a universal decoupling strategy guides the search direction and addresses coupling problems, thereby accelerating the search process. Experimental results on three types of PDEs demonstrate that our method can reliably obtain human-understandable symbolic expressions that fit both the PDEs and the numerical solutions from traditional methods. This work advances multiphysics simulation by enhancing our ability to derive approximate symbolic solutions for PDEs, thereby improving our understanding of complex physical phenomena. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Numerical methods

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Yuexiao Li, Huixia Zheng, Xiawu Xiao, Xuefeng Wang, Rui Wen, Shilei Pan, Xin Chao, Fei Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University 361005 China ByteDance Inc. China Peng Cheng Laboratory Shenzhen China Shenzhen Research Institute of Xiamen University China

Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. In this paper, we take the initiative to explore and present a theoretical proof to explain why such a problem is essential in PTQ. And then, we try to solve this problem by introducing a principled and generalized framework theoretically. In particular, we first formulate the oscillation in PTQ and prove the problem is caused by the difference in module capacity. To this end, we define the module capacity (ModCap) under data-dependent and data-free scenarios, where the differentials between adjacent modules are used to measure the degree of oscillation. The problem is then solved by selecting top-k differentials, in which the corresponding modules are jointly optimized and quantized. Extensive experiments demonstrate that our method successfully reduces the performance drop and is generalized to different neural networks and PTQ methods. For example, with 2/4 bit ResNet-50 quantization, our method surpasses the previous state-of-the-art method by 1.9%. It becomes more significant on small model quantization, e.g. surpasses BRECQ method by 6.61% on MobileNetV2 ×0.5. Copyright © 2023, The Authors. All rights reserved.

关键词： Data privacy