检索结果-内蒙古大学图书馆

34th ACM Web Conference, WWW 2025

作者： Han, Shen Zhou, Zhiyao Chen, Jiawei Hao, Zhezheng Zhou, Sheng Wang, Gang Feng, Yan Chen, Chun Wang, Can The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University China Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security China Northwestern Polytechnical University Xi’an China Bangsun Technology Hangzhou China

ISBN: (纸本)9798400712746

Graph Neural Networks (GNNs) have become a prominent approach for learning from graph-structured data. However, their effectiveness can be significantly compromised when the graph structure is suboptimal. To address this issue, Graph Structure Learning (GSL) has emerged as a promising technique that refines node connections adaptively. Nevertheless, we identify two key limitations in existing GSL methods: 1) Most methods primarily focus on node similarity to construct relationships, while overlooking the quality of node information. Blindly connecting low-quality nodes and aggregating their ambiguous information can degrade the performance of other nodes. 2) The constructed graph structures are often constrained to be symmetric, which may limit the model’s flexibility and effectiveness. To overcome these limitations, we propose an Uncertainty-aware Graph Structure Learning (UnGSL) strategy. UnGSL estimates the uncertainty of node information and utilizes it to adjust the strength of directional connections, where the influence of nodes with high uncertainty is adaptively reduced. Importantly, UnGSL serves as a plug-in module that can be seamlessly integrated into existing GSL methods with minimal additional computational cost. In our experiments, we implement UnGSL into six representative GSL methods, demonstrating consistent performance improvements. © 2025 Copyright held by the owner/author(s).

关键词： Graph Neural Network Graph Structure Learning Uncertainty

来源：评论

学校读者我要写书评

暂无评论

TRAIN SMALL, INFER LARGE: MEMORY-EFFICIENT LORA TRAINING FOR LARGE LANGUAGE MODELS

arXiv

引用

arXiv 2025年

作者： Zhang, Jun Wang, Jue Li, Huan Shou, Lidan Chen, Ke You, Yang Xie, Guiming Gong, Xuejian Zhou, Kunlong The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China College of Computer Science and Technology Zhejiang University China Department of Computer Science National University of Singapore Singapore AI Center Guangdong OPPO Mobile Telecommunications Corp. Ltd. China

Large Language Models (LLMs) have significantly advanced natural language processing with exceptional task generalization capabilities. Low-Rank Adaption (LoRA) offers a cost-effective fine-tuning solution, freezing the original model parameters and training only lightweight, low-rank adapter matrices. However, the memory footprint of LoRA is largely dominated by the original model parameters. To mitigate this, we propose LORAM, a memory-efficient LoRA training scheme founded on the intuition that many neurons in over-parameterized LLMs have low training utility but are essential for inference. LORAM presents a unique twist: it trains on a pruned (small) model to obtain pruned low-rank matrices, which are then recovered and utilized with the original (large) model for inference. Additionally, minimal-cost continual pre-training, performed by the model publishers in advance, aligns the knowledge discrepancy between pruned and original models. Our extensive experiments demonstrate the efficacy of LORAM across various pruning strategies and downstream tasks. For a model with 70 billion parameters, LORAM enables training on a GPU with only 20G HBM, replacing an A100-80G GPU for LoRA training and 15 GPUs for full fine-tuning. Specifically, QLORAM implemented by structured pruning combined with 4-bit quantization, for LLaMA-3.1-70B (LLaMA-2-70B), reduces the parameter storage cost that dominates the memory usage in low-rank matrix training by 15.81× (16.95×), while achieving dominant performance gains over both the original LLaMA-3.170B (LLaMA-2-70B) and LoRA-trained LLaMA-3.1-8B (LLaMA-2-13B). Code is available at https://***/junzhang-zj/LoRAM. © 2025, CC BY.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

arXiv

引用

arXiv 2025年

作者： Lyu, Kedi Chen, Haipeng Liu, Zhenguang Yin, Yifang Lin, Yukang Jiao, Yingying College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China A*STAR Singapore Tsinghua Shenzhen International Graduate School Nanshan District Shenzhen China

Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, it proves to be markedly more challenging for machines to emulate. To bridge the gap, we propose the Human-like Vision and Inference System (HVIS) for human motion prediction, which is designed to emulate human observation and forecast future movements. HVIS comprises two components: the human-like vision encode (HVE) module and the human-like motion inference (HMI) module. The HVE module mimics and refines the human visual process, incorporating a retina-analog component that captures spatiotemporal information separately to avoid unnecessary crosstalk. Additionally, a visual cortex-analogy component is designed to hierarchically extract and treat complex motion features, focusing on both global and local features of human poses. The HMI is employed to simulate the multi-stage learning model of the human brain. The spontaneous learning network simulates the neuronal fracture generation process for the adversarial generation of future motions. Subsequently, the deliberate learning network is optimized for hard-to-train joints to prevent misleading learning. Experimental results demonstrate that our method achieves new state-of-the-art performance, significantly outperforming existing methods by 19.8% on Human3.6M, 15.7% on CMU Mocap, and 11.1% on G3D. © 2025, CC BY.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

arXiv

引用

arXiv 2025年

作者： Wang, Zhigang Fan, Shaojing Liu, Zhenguang Wu, Zheqi Wu, Sifan Jiao, Yingying College of Computer Science and Technology Zhejiang Gongshang University Hangzhou China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatio-temporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset. © 2025, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

Multi-Grained Feature Pruning for Video-Based Human Pose Est...

引用

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

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Preventing the Popular Item Embedding Based Attack in Federated Recommendations

arXiv

引用

arXiv 2025年

作者： Zhang, Jun Li, Huan Rong, Dazhong Zhao, Yan Chen, Ke Shou, Lidan The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Department of Computer Science Aalborg University Aalborg Denmark

Privacy concerns have led to the rise of federated recommender systems (FRS), which can create personalized models across distributed clients. However, FRS is vulnerable to poisoning attacks, where malicious users manipulate gradients to promote their target items intentionally. Existing attacks against FRS have limitations, as they depend on specific models and prior knowledge, restricting their real-world applicability. In our exploration of practical FRS vulnerabilities, we devise a model-agnostic and prior-knowledge-free attack, named PIECK (Popular Item Embedding based Attack). The core module of PIECK is popular item mining, which leverages embedding changes during FRS training to effectively identify the popular items. Built upon the core module, PIECK branches into two diverse solutions: The PIECKIPE solution employs an item popularity enhancement module, which aligns the embeddings of targeted items with the mined popular items to increase item exposure. The PIECKUEA further enhances the robustness of the attack by using a user embedding approximation module, which approximates private user embeddings using mined popular items. Upon identifying PIECK, we evaluate existing federated defense methods and find them ineffective against PIECK, as poisonous gradients inevitably overwhelm the cold target items. We then propose a novel defense method by introducing two regularization terms during user training, which constrain item popularity enhancement and user embedding approximation while preserving FRS performance. We evaluate PIECK and its defense across two base models, three real datasets, four top-tier attacks, and six general defense methods, affirming the efficacy of both PIECK and its defense. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

Multi-Grained Feature Pruning for Video-Based Human Pose Est...

引用

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

作者： Zhigang Wang Shaojing Fan Zhenguang Liu Zheqi Wu Sifan Wu Yingying Jiao College of Computer Science and Technology Zhejiang Gongshang University Hangzhou China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatiotemporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset.

关键词： Accuracy Pose estimation Semantics Signal processing algorithms Benchmark testing Signal processing Motion capture Computational efficiency Spatiotemporal phenomena Speech processing

来源：评论

学校读者我要写书评

暂无评论

InTime: Towards Performance Predictability In Byzantine Fault Tolerant Proof-of-Stake Consensus

引用

Proceedings of the ACM on Management of data 2025年第1期3卷 1-27页

作者： Weijie Sun Zihuan Xu Wangze Ni Lei Chen The Hong Kong University of Science and Technology Hong Kong Hong Kong Shenzhen Institute of Computing Sciences Shenzhen China Zhejiang University Hangzhou China The State Key Laboratory of Blockchain and Data Security Hangzhou China & Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China The Hong Kong University of Science and Technology Hong Kong Hong Kong & HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

Performance predictability, ensuring low latency variability, is crucial for the reliability and efficiency of blockchain consensus. Byzantine Fault Tolerant Proof-of-Stake (BFT-PoS) consensus aims to achieve stable transaction processing latency by scheduling block generation at consistent intervals. However, BFT-PoS's incentive mechanisms grant all transaction tips to the block proposer, which can be exploited by delaying proposals to gain extra Maximal Extractable Value (MEV) rewards, thus undermining performance predictability. Existing solutions impose penalties for delays but lack a standard for measuring the extra rewards from delays or fail in malicious *** paper introduces InTime, a novel approach to safeguard performance predictability in BFT-PoS by economically motivating timely block proposals. We first introduce the untimely MEV ratio, a reliable metric to measure the extra rewards gained from proposal delays, facilitating our countermeasures against deliberate delays. Furthermore, we propose the arrival rate incentive (ARI), aligning rewards with transaction arrival timing among nodes to reduce potential MEV manipulation. To make ARI robust against malicious behaviors, we establish a committee time witness (CTW) workflow to accurately gather and verify transaction arrival times. Extensive experiments demonstrate that InTime can effectively reduce latency variability by up to 95.9%.

关键词： PoS consensus blockchain incentive design

来源：评论

学校读者我要写书评

暂无评论

Mamba Adapter: Efficient Multi-Modal Fusion for Vision-Language Tracking

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Shi, Liangtao Zhong, Bineng Liang, Qihua Hu, Xiantao Mo, Zhiyi Song, Shuxiang Ministry of Education Guangxi Normal University Key Laboratory of Education Blockchain and Intelligent Technology Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Wuzhou University School of Data Science and Software Engineering Wuzhou543002 China

Utilizing the high-level semantic information of language to compensate for the limitations of vision information is a highly regarded approach in single-object tracking. However, most existing vision-language (VL) trackers employ full-parameter fine-tuning, which can easily lead to catastrophic forgetting. Therefore, they fail to fully exploit the prior knowledge of pre-trained models from upstream tasks, resulting in unsatisfactory tracking performance. To alleviate the above problem, we propose a simple yet effective Vision-Language Tracking pipeline based on Mamba Adapter, named MAVLT, which adopts the idea of parameter-efficient fine-tuning (PEFT) to realize the interaction between vision-language modalities. This novel approach offers the following advantages: (1)The knowledge of the upstream pre-trained model is efficiently inherited by freezing its parameters. This ensures that the VL tracking framework only learns the modules for vision and language interaction, with a focus on the fusion between modalities. (2)The modal interaction between language and vision encoders is flexibly bridged in each encoder layer via proposed mamba adapter, enabling efficient interaction of visual and language information at multiple levels. Extensive experiments on five popular vision-language tracking benchmarks validate the effectiveness of the proposed MAVLT. Particularly, the MAVLT achieves 73.4% AUC score on the LaSOT benchmarks with only 0.18%(0.32M) of the total parameters updates. Code and models are available at https://***/GXNU-ZhongLab/MAVLT. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：