检索结果-内蒙古大学图书馆

Community-Centric Graph Unlearning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yi Zhang, Shichao Zhang, Guixian Cheng, Debo Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China School of Computer Science and Technology China University of Mining and Technology Xuzhou Jiangsu221116 China UniSA STEM University of South Australia Mawson Lakes Adelaide Australia

Graph unlearning technology has become increasingly important since the advent of the ‘right to be forgotten’ and the growing concerns about the privacy and security of artificial intelligence. Graph unlearning aims to quickly eliminate the effects of specific data on graph neural networks (GNNs). However, most existing deterministic graph unlearning frameworks follow a balanced partition-submodel training-aggregation paradigm, resulting in a lack of structural information between subgraph neighborhoods and redundant unlearning parameter calculations. To address this issue, we propose a novel Graph Structure Mapping Unlearning paradigm (GSMU) and a novel method based on it named Community-centric Graph Eraser (CGE). CGE maps community subgraphs to nodes, thereby enabling the reconstruction of a node-level unlearning operation within a reduced mapped graph. CGE makes the exponential reduction of both the amount of training data and the number of unlearning parameters. Extensive experiments conducted on five real-world datasets and three widely used GNN backbones have verified the high performance and efficiency of our CGE method, highlighting its potential in the field of graph unlearning. https://***/liiiyi/CCGU © 2024, CC BY-NC-ND.

关键词： Graph neural networks

Learning Hybrid Negative Probability Model for Weakly-Supervised Whole Slide Image Recognition

学校读者我要写书评

暂无评论

Learning Hybrid Negative Probability Model for Weakly-Superv...

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

作者： Yining Qiu Yuxi Li Jiafu Wu Zhenye Gan Mingmin Chi Yabiao Wang Chengjie Wang Pei Wang School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China Tencent Youtu Lab China Zhongshan PoolNet Technology Co. Ltd Zhongshan Fudan Joint Innovation Center China Zhejiang University China NAOC CAS China

Classifying an entire Whole Slide Image (WSI) in a single forward pass is challenging due to its vast resolution. Consequently, current effort on WSI classification resorts to multiple instance learning (MIL), using patch-wise instances to predict categories under image-wise supervision. However, recent MIL methods usually follow implicit instance selection strategy and ignore the effect from inherent patch category imbalances. In a statistical sense, negative patches dominate in WSIs and provide sufficient samples for accurate density estimation. Therefore, in this paper, we learn from anomaly detection and propose a deep MIL framework which learns a hybrid negative probability model to bootstrap discovery of potential positive lesion. We associate attention-based MIL approach with a regularization loss function to explicitly improve patch selection process in positive images. Experiments conducted on benchmarks of WSI recognition demonstrate that our method brings significant improvement to classic attention-based MIL baseline and achieves state-of-the-art performance.

关键词：

Optimal Hub Placement and Deadlock-Free Routing for Payment Channel Network Scalability

学校读者我要写书评

暂无评论

Optimal Hub Placement and Deadlock-Free Routing for Payment ...

International Conference on Distributed Computing Systems

作者： Lingxiao Yang Xuewen Dong Sheng Gao Qiang Qu Xiaodong Zhang Wensheng Tian Yulong Shen School of Computer Science and Technology Xidian University Xi'an China School of Information Central University of Finance and Economics Beijing China Shenzhen Institute of Advanced Techbology Chinese Academy of Sciences Huawei Blockchain Lab Huawei Cloud Tech Co. Ltd Shenzhen China Nanhu Lab Jiaxing China

As a promising implementation model of payment channel network (PCN), payment channel hub (PCH) could achieve high throughput by providing stable off-chain transactions through powerful hubs. However, existing PCH schemes assume hubs are preplaced in advance, not considering payment requests' distribution and may affect network scalability, especially network load balancing. In addition, current source routing protocols with PCH allow each sender to make routing decision on his/her own request, which may have a bad effect on performance scalability (e.g., deadlock) for not considering other senders' requests. This paper proposes a novel multi-PCHs solution with high scalability. First, we are the first to study the PCH placement problem and propose optimal/approximation solutions with load balancing for small-scale and large-scale scenarios, by trading off communication costs among participants and turning the original NP-hard problem into a mixed-integer linear programming (MILP) problem solving by supermodular techniques. Then, on global network states and local directly connected clients' requests, a routing protocol is designed for each PCH with a dynamic adjustment strategy on request processing rates, enabling high-performance deadlock-free routing. Extensive experiments show that our work can effectively balance the network load, and improve the performance on throughput by 29.3% on average compared with state-of-the-arts.

关键词：

Mamba-YOLO-World: Marrying YOLO-World with Mamba for Open-Vocabulary Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Haoxuan He, Qingdong Peng, Jinlong Yang, Hao Chi, Mingmin Wang, Yabiao School of computer science Shanghai key laboratory of data science Fudan University China Tencent Youtu Lab China Shanghai Jiao Tong University China Zhongshan PoolNet Technology Co. Ltd. Zhongshan Fudan Joint Innovation Center China

Open-vocabulary detection (OVD) aims to detect objects beyond a predefined set of categories. As a pioneering model incorporating the YOLO series into OVD, YOLO-World is well-suited for scenarios prioritizing speed and efficiency. However, its performance is hindered by its neck feature fusion mechanism, which causes the quadratic complexity and the limited guided receptive fields. To address these limitations, we present Mamba-YOLO-World, a novel YOLO-based OVD model employing the proposed MambaFusion Path Aggregation Network (MambaFusion-PAN) as its neck architecture. Specifically, we introduce an innovative State Space Model-based feature fusion mechanism consisting of a Parallel-Guided Selective Scan algorithm and a Serial-Guided Selective Scan algorithm with linear complexity and globally guided receptive fields. It leverages multi-modal input sequences and mamba hidden states to guide the selective scanning process. Experiments demonstrate that our model outperforms the original YOLO-World on the COCO and LVIS benchmarks in both zero-shot and fine-tuning settings while maintaining comparable parameters and FLOPs. Additionally, it surpasses existing state-of-the-art OVD methods with fewer parameters and FLOPs. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Zhirong Zhang, Shichao Cheng, Debo Li, Jiuyong Liu, Lin Zhang, Guixian Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China UniSA STEM University of South Australia Mawson Lakes Adelaide Australia School of Computer Science and Technology China University of Mining and Technology Jiangsu Xuzhou221116 China

In recommender systems, popularity and conformity biases undermine recommender effectiveness by disproportionately favouring popular items, leading to their over-representation in recommendation lists and causing an unbalanced distribution of user-item historical data. We construct a causal graph to address both biases and describe the abstract data generation mechanism. Then, we use it as a guide to develop a novel Debiased Contrastive Learning framework for Mitigating Dual Biases, called DCLMDB. In DCLMDB, both popularity bias and conformity bias are handled in the model training process by contrastive learning to ensure that user choices and recommended items are not unduly influenced by conformity and popularity. Extensive experiments on two real-world datasets, Movielens-10M and Netflix, show that DCLMDB can effectively reduce the dual biases, as well as significantly enhance the accuracy and diversity of recommendations. © 2024, CC BY-NC-ND.

关键词： Contrastive Learning

Rack-Aware Minimum Storage Partially Cooperative Regenerating Codes with Small Sub-Packetization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Hengming Wu, Dianhua Cheng, Minquan School of Computer Science and Engineering Guangxi Normal University Guilin541004 China School of Mathematics and Statistics Nanning Normal University Nanning530100 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China School of Mathematics and Statistics Guangxi Normal University Guilin541006 China

In the rack-aware model, there are n¯ racks each of which has u nodes with the same storage capacity. Assume that there are h failed nodes uniformly distributed in h¯ host racks (defined as racks containing failed nodes), each rack containing h/h¯ failed nodes where h is divisible by h¯. Then together with its internal helper nodes, each host rack downloads recovery data from d¯ helper racks and repairs its failed nodes. The repair bandwidth is defined as the total inter-rack data transfer required for failures recovery, as the intra-rack communication does not contribute to this cost. The full cooperative repair model requires that each host rack must exchange the data with all the other h¯ host racks during the cooperative repair phase. However, in the partial cooperative repair model, each host rack only needs to exchange data with h¯ − δ (1 ≤ δ ≤ h¯ − 1) other host racks, during the cooperative repair phase. In this paper, we focus on the rack-aware minimum storage partially cooperative regenerating (MSPCR) codes for repairing the h node failures. We first derive the lower bound on the repair bandwidth for rack-aware MSPCR codes using extremal combinatorics, and then construct two classes of optimal repair schemes for rack-aware MSPCR codes with small sub-packetization level. In particular, when δ = 1, our second codes reduce to rack-aware minimum-storage cooperative regenerating (MSCR) codes, while achieving an (h¯ + 1)-fold reduction in sub-packetization level compared to known rack-aware MSCR codes. Copyright © 2025, The Authors. All rights reserved.

关键词： Static random access storage

Discrete Curvature Graph Information Bottleneck

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fu, Xingcheng Wang, Jian Gao, Yisen Sun, Qingyun Yuan, Haonan Li, Jianxin Li, Xianxian Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University China Institute of Artificial Intelligence Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

Graph neural networks(GNNs) have been demonstrated to depend on whether the node effective information is sufficiently passing. Discrete curvature (Ricci curvature) is used to study graph connectivity and information propagation efficiency with a geometric perspective, and has been raised in recent years to explore the efficient message-passing structure of GNNs. However, most empirical studies are based on directly observed graph structures or heuristic topological assumptions and lack in-depth exploration of underlying optimal information transport structures for downstream tasks. We suggest that graph curvature optimization is more in-depth and essential than directly rewiring or learning for graph structure with richer message-passing characterization and better information transport interpretability. From both graph geometry and information theory perspectives, we propose the novel Discrete Curvature Graph Information Bottleneck (CurvGIB) framework to optimize the information transport structure and learn better node representations simultaneously. CurvGIB advances the Variational Information Bottleneck (VIB) principle for Ricci curvature optimization to learn the optimal information transport pattern for specific downstream tasks. The learned Ricci curvature is used to refine the optimal transport structure of the graph, and the node representation is fully and efficiently learned. Moreover, for the computational complexity of Ricci curvature differentiation, we combine Ricci flow and VIB to deduce a curvature optimization approximation to form a tractable IB objective function. Extensive experiments on various datasets demonstrate the superior effectiveness and interpretability of CurvGIB. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

An Efficient and Reliable Asynchronous Federated Learning Scheme for Smart Public Transportation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xu, Chenhao Qu, Youyang Luan, Tom H. Eklund, Peter W. Xiang, Yong Gao, Longxiang The Deakin Blockchain Innovation Lab School of Information Technology Deakin University Geelong Australia Data 61 Australia Commonwealth Scientific and Industrial Research Organization Australia School of Cyber Engineering Xidian University Shaanxi China School of Information Technology Deakin University Geelong Australia Qilu University of Technology Shandong Computer Science Center China

Since the traffic conditions change over time, machine learning models that predict traffic flows must be updated continuously and efficiently in smart public transportation. Federated learning (FL) is a distributed machine learning scheme that allows buses to receive model updates without waiting for model training on the cloud. However, FL is vulnerable to poisoning or DDoS attacks since buses travel in public. Some work introduces blockchain to improve reliability, but the additional latency from the consensus process reduces the efficiency of FL. Asynchronous Federated Learning (AFL) is a scheme that reduces the latency of aggregation to improve efficiency, but the learning performance is unstable due to unreasonably weighted local models. To address the above challenges, this paper offers a blockchain-based asynchronous federated learning scheme with a dynamic scaling factor (DBAFL). Specifically, the novel committee-based consensus algorithm for blockchain improves reliability at the lowest possible cost of time. Meanwhile, the devised dynamic scaling factor allows AFL to assign reasonable weights to stale local models. Extensive experiments conducted on heterogeneous devices validate outperformed learning performance, efficiency, and reliability of DBAFL. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

CovKG: A Covid-19 Knowledge Graph for enabling multidimensional analytics on Covid-19 epidemiological data considering spatiotemporal, environmental, health, and socioeconomic aspects

学校读者我要写书评

暂无评论

International Journal of Information Management Data Insights 2025年第1期5卷

作者： Deb Nath, Rudra Pratap Raihan, S.M. Shafkat Das, Tonmoy Chandro Pedersen, Torben Bach Ghose, Debasish Big Data Information and Knowledge Engineering Lab Department of Computer Science and Engineering University of Chittagong Chattogram 4331 Bangladesh Department of Computer Science Aalborg University Aalborg 9220 Denmark School of Economics Innovation and Technology Kristiania University College State Three Bergen 0153 Norway

The Covid-19 pandemic is influenced by many environmental, health, and socioeconomic aspects such as air pollution, comorbidity, occupation, etc. To better manage future pandemics, decision-makers need comprehensive data on Covid-19 mortality and morbidity. Most Covid-19 data sources focus on spatiotemporal aspects, and existing research often overlook the combined impact of multiple interconnected factors. This study introduces a Covid-19 Knowledge Graph (CovKG) derived from 20 data sources, enabling multidimensional analysis of epidemiological data, including time, location, temperature, comorbidity, occupation, and others. CovKG is modeled using RDF, connected to 10,951 external resources, and semantically enriched with Data Cube (QB) and QB for OLAP (QB4OLAP) vocabularies to adhere to the FAIR principles and ensure OLAP compatibility. Finally, we perform a qualitative and comparative evaluation and extract statistical insights across multiple dimensions of Covid-19 epidemiology. When assessed, CovKG answers 100% of competency queries, outperforming other data stores that only answer 39%. CovKG and its analytical interface are available at https://***/datasets/CovKG/. © 2025 The Authors

关键词： Covid-19 FAIR principles Knowledge Graph Linked data Multidimensional analysis Semantic technology