检索结果-内蒙古大学图书馆

FTA-FTL: A Fine-Tuned Aggregation Federated Transfer Learning Scheme for Lithology Microscopic Image Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： RahimiZadeh, Keyvan Taheri, Ahmad Baumbach, Jan Makarian, Esmael Dehghani, Abbas Ravaei, Bahman Javadi, Bahman Beheshti, Amin School of Computing Macquarie University SydneyNSW2109 Australia Institute of Computational Systems Biology University of Hamburg Notkestrasse 9 Hamburg22607 Germany Department of Mining Engineering Sahand University of Technology Tabriz513351996 Iran Department of Computer Engineering School of Engineering Yasouj University Yasouj*** Iran School of Computer Data and Mathematical Sciences Western Sydney University NSW2751 Australia

Lithology discrimination is a crucial activity in characterizing oil reservoirs, and processing lithology microscopic images is an essential technique for investigating fossils and minerals and geological assessment of shale oil exploration. In this way, Deep Learning (DL) technique is a powerful approach for building robust classifier models. However, there is still a considerable challenge to collect and produce a large dataset. Transfer-learning and data augmentation techniques have emerged as popular approaches to tackle this problem. Furthermore, due to different reasons, especially data privacy, individuals, organizations, and industry companies often are not willing to share their sensitive data and information. Federated Learning (FL) has emerged to train a highly accurate central model across multiple decentralized edge servers without transferring sensitive data, preserving sensitive data, and enhancing security. This study involves two phases;the first phase is to conduct Lithology microscopic image classification on a small dataset using transfer learning. In doing so, various pre-trained DL model architectures are comprehensively compared for the classification task. In the second phase, we formulated the classification task to a Federated Transfer Learning (FTL) scheme and proposed a Fine-Tuned Aggregation strategy for Federated Learning (FTA-FTL). In order to perform a comprehensive experimental study, several metrics such as accuracy, f1 score, precision, specificity, sensitivity (recall), and confusion matrix are taken into account. The results are in excellent agreement and confirm the efficiency of the proposed scheme, and show that the proposed FTA-FTL algorithm is capable enough to achieve approximately the same results obtained by the centralized implementation for Lithology microscopic images classification task. © 2025, CC BY.

关键词： Sensitive data

DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yu, Guoqi Li, Yaoming Wang, Juncheng Guo, Xiaoyu Aviles-Rivero, Angelica I. Yang, Tong Wang, Shujun Department of Biomedical Engineering The Hong Kong Polytechnic University Hong Kong Data Structures Laboratory School of Computer Science Peking University Beijing China DAMTP University of Cambridge Cambridge United Kingdom

Recent advancements have progressively incorporated frequency-based techniques into deep learning models, leading to notable improvements in accuracy and efficiency for time series analysis tasks. However, the Mid-Frequency Spectrum Gap in the real-world time series, where the energy is concentrated at the low-frequency region while the middle-frequency band is negligible, hinders the ability of existing deep learning models to extract the crucial frequency information. Additionally, the shared Key-Frequency in multivariate time series, where different time series share indistinguishable frequency patterns, is rarely exploited by existing literature. This work introduces a novel module, Adaptive Mid-Frequency Energy Optimizer, based on convolution and residual learning, to emphasize the significance of mid-frequency bands. We also propose an Energy-based Key-Frequency Picking Block to capture shared Key-Frequency, which achieves superior inter-series modeling performance with fewer parameters. A novel Key-Frequency Enhanced Training strategy is employed to further enhance Key-Frequency modeling, where spectral information from other channels is randomly introduced into each channel. Our approach advanced multivariate time series forecasting on the challenging Traffic, ECL, and Solar benchmarks, reducing MSE by 4%, 6%, and 5% compared to the previous SOTA iTransformer. Code is available at this GitHub Repository: https://***/Levi-Ackman/ReFocus. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning

LESA: Learnable LLM Layer Scaling-Up

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Yifei Cao, Zouying Ma, Xinbei Yao, Yao Qin, Libo Chen, Zhi Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China School of Computer Science and Engineering Central South University China ByteDance China

Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. However, existing depth scaling-up methods rely on empirical heuristic rules for layer duplication, which result in poorer initialization and slower convergence during continual pre-training. We propose LESA, a novel learnable method for depth scaling-up. By concatenating parameters from each layer and applying Singular Value Decomposition, we uncover latent patterns between layers, suggesting that inter-layer parameters can be learned. LESA uses a neural network to predict the parameters inserted between adjacent layers, enabling better initialization and faster training. Experiments show that LESA outperforms existing baselines, achieving superior performance with less than half the computational cost during continual pre-training. Extensive analyses demonstrate its effectiveness across different model sizes and tasks.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Multilayer neural networks

Low-light Image Enhancement through Learning a Simplified Inverse Rendering Model

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wu, Wenhui Pang, Jia Gao, Shuaibo Zhang, Pingping Chen, Zhe Qiu, Guoping Shenzhen University College of Electronics and Information Engineering China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China City University of Hong Kong Department of Computer Science Hong Kong University of Nottingham School of Computer Science United Kingdom

It remains to be extremely difficult to capture high quality photographs of low-light scenes. Low light causes the low signal-to-noise ratio (SNR) problem which makes the image noisy. Such scenes almost always have the high dynamic range (HDR) problem caused by uneven lighting where a small area surrounding the light source is very bright while the rest of the scene is very dark, making it very difficult to simultaneously obtain high quality signals in both the dark and bright areas. This paper presents a new image restoration method for tackling the problems in low-light scenes. Fundamentally differing from existing approaches, the new method borrows ideas from inverse graphics rendering and re-renders the image with a canonical light source thus correcting the image from first principle. A deep learning based simplified inverse rendering model (SIRM) featuring implicit regularization is first developed for correcting uneven lighting and then an end-to-end convolutional neural network is constructed for reducing noise. Extensive experimental results are presented to demonstrate that the new method outperforms state-of-the-art methods, and is capable of effectively brightening up dark image regions while at the same time preserving details and color consistency. Our code is available at: https://***/pj0927/SIRNet. © 2025 IEEE.

关键词： Rendering (computer graphics)

Personalized Federated Learning with Enhanced Implicit Generalization

学校读者我要写书评

暂无评论

Personalized Federated Learning with Enhanced Implicit Gener...

International Joint Conference on Neural Networks (IJCNN)

作者： Heping Liu Songbai Liu Junkai Ji Qiuzhen Lin Jianyong Chen Kay Chen Tan College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computing The Hong Kong Polytechnic University

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Integrating personalization into federated learning is crucial for addressing data heterogeneity and surpassing the limitations of a single aggregated model. Personalized federated learning excels at capturing inter-client similarities and meeting diverse client needs through custom-made models. However, even with personalized approaches, it’s essential to aggregate knowledge among clients to ensure universal benefits. This paper proposes Federated Dual Objectives and Dual Models (FedDodm), a novel approach that employs two independent models to separately address explicit personalization and implicit generalization objectives in personalized federated learning. By treating these objectives as distinct loss functions and training models accordingly, we achieve a balance between the two through a fusion method. Extensive experiments across various models and learning tasks demonstrate that FedDodm outperforms state-of-the-art federated learning approaches, marking a significant advancement in effectively integrating personalized and generalized knowledge.

关键词： Training Federated learning Aggregates Neural networks data models

SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cao, Zouying Yang, Yifei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue, limiting their helpfulness. In this paper, we propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns in aligned LLMs. First, SCANS extracts the refusal steering vectors within the activation space and utilizes vocabulary projection to anchor some specific safety-critical layers which influence model refusal behavior. Second, by tracking the hidden state transition, SCANS identifies the steering direction and steers the model behavior accordingly, achieving a balance between exaggerated safety and adequate safety. Experiments show that SCANS achieves new state-of-the-art performance on XSTest and OKTest benchmarks, without impairing their defense capability against harmful queries and maintaining almost unchanged model capability. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Service Function Chain Dynamic Scheduling in Space-Air-Ground Integrated Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Jia, Ziye Cao, Yilu He, Lijun Wu, Qihui Zhu, Qiuming Niyato, Dusit Han, Zhu Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China Xidian University State Key Laboratory of ISN Xian710071 China China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Nanyang Technological University School of Computer Science and Engineering Singapore639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

As an important component of the sixth generation communication technologies, the space-air-ground integrated network (SAGIN) attracts increasing attentions in recent years. However, due to the mobility and heterogeneity of the components such as satellites and unmanned aerial vehiclesin multi-layer SAGIN, the challenges of inefficient resource allocation and management complexity are aggregated. To this end, the network function virtualization technology is introduced and can be implemented via service function chains (SFCs) deployment. However, urgent unexpected tasks may bring conflicts and resource competition during SFC deployment, and how to schedule the SFCs of multiple tasks in SAGIN is a key issue. In this paper, we address the dynamic and complexity of SAGIN by presenting a reconfigurable time extension graph and further propose the dynamic SFC scheduling model. Then, we formulate the SFC scheduling problem to maximize the number of successful deployed SFCs within limited resources and time horizons. Since the problem is in the form of integer linear programming and intractable to solve, we propose the algorithm by incorporating deep reinforcement learning. Finally, simulation results show that the proposed algorithm has better convergence and performance compared to other benchmark algorithms. © 2025 IEEE.

关键词： Network function virtualization

M2G4RTP: A Multi-Level and Multi-Task Graph Model for Instant-Logistics Route and Time Joint Prediction

学校读者我要写书评

暂无评论

M2G4RTP: A Multi-Level and Multi-Task Graph Model for Instan...

International Conference on data engineering

作者： Tianyue Cai Huaiyu Wan Fan Wu Haomin Wen Shengnan Guo Lixia Wu Haoyuan Hu Youfang Lin School of Computer and Information Technology Beijing Jiaotong University Beijing China Artificial Intelligence Department Cainiao Network Hangzhou China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing China

Instant-logistics (e.g., food delivery and package pick-up) is increasingly calling for Route and Time Prediction (RTP), which aims to predict both future route and arrival time of a courier’s unvisited locations. Accurate RTP can greatly benefit the platform, such as optimizing order dispatching and improving user experience. Although recent years have witnessed various works for solving the RTP problem, they still suffer from the following three limitations: i) Failing to consider the high-level transfer mode of couriers between AOIs (Areas Of Interest, such as residential quarters or office buildings), which can help to build more accurate RTP. ii) Failing to simultaneously make the route and time prediction. Existing works either separately predict route/time or predict them in a two-step way. However, since route and time are strongly correlated (nearby locations in the route should have similar arrival times), jointly predicting them should be more effective. iii) The widely adopted tree-based or sequence-based architecture fails to fully encode the spatial relationship between different locations. To address the above limitations, we propose a multi-level and multi-task graph model, named M 2 G4RTP, for instant-logistics route and time joint prediction. Specifically, we propose a multi-level graph encoder equipped with a newly-designed GAT-e encoding module to capture couriers’ both high-level transfer modes between AOIs and low-level transfer modes between locations. Moreover, a multi-task decoder is presented to jointly predict the route and time at different levels. Finally, a loss weighting method based on homoscedastic uncertainty is designed to balance the two tasks adaptively. Extensive experiments on an industry-scale real-world dataset, as well as the online deployment on Cainiao Alibaba, demonstrate the superiority of our proposed model.

关键词：