检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learning

arXiv

引用

arXiv 2025年

作者： Liu, Bangzhen Zheng, Chenxi Xu, Xuemiao Xu, Cheng Zhang, Huaidong He, Shengfeng South China University of Technology Guangzhou China Guangdong Engineering Center for Large Model and GenAI Technology The State Key Laboratory of Subtropical Building and Urban Science The Ministry of Education Key Laboratory of Big Data and Intelligent Robot The Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Singapore Management University Singapore

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ an orientation-aware contrastive learning framework that incorporates an orientation consistency loss and a margin separation loss, enabling effective learning of categorically discriminative and generalizable features with rotation consistency. Extensive experiments and ablations conducted on 3D cross-domain benchmarks firmly establish the state-of-the-art performance of our proposed approach in the context of orientation-aware 3D domain generalization. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Sharing, Teaching and Aligning: knowledgeable Transfer Learning for Cross-Lingual Machine Reading Comprehension

arXiv

引用

arXiv 2023年

作者： Cao, Tingfeng Wang, Chengyu Tan, Chuanqi Huang, Jun Zhu, Jinhui School of Software Engineering South China University of Technology China Alibaba Group China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to the source to aid inference. However, in cross-lingual machine reading comprehension (MRC), it is difficult to perform a deep level of assistance to enhance cross-lingual transfer because of the variation of answer span positions in different languages. In this paper, we propose X-STA, a new approach for cross-lingual MRC. Specifically, we leverage an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target. A Gradient-Disentangled knowledge Sharing technique is proposed as an improved cross-attention block. In addition, we force the model to learn semantic alignments from multiple granularities and calibrate the model outputs with teacher guidance to enhance cross-lingual transferability. Experiments on three multi-lingual MRC datasets show the effectiveness of our method, outperforming state-of-the-art approaches. 1 Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Densely packed object detection with transformer-based head and EM-merger

Densely packed object detection with transformer-based head ...

引用

作者： Zhong, Xiaojing Zhang, Ni Hu, Hao Li, Li Cen, Junhua Wu, Qingyao School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China Pazhou Lab Guangzhou China Peng Cheng Laboratory Guangzhou China Zhongnan Building Materials Group Co. Ltd. Guangdong GW Guangzhou China Internet Technology Co. Ltd. Guangdong GW Guangzhou China

Due to the high density of objects and their varying sizes, detecting them accurately and without repetition in such scenarios is more challenging than traditional object detection methods. In this paper, we propose a YOLOv5-based object detection approach equipped with a Transformer-based Head and EM-Merger unit specifically designed for densely packed scenes. We incorporate the transformer architecture into the prediction heads to enable a self-attention mechanism that captures long-term dependencies between the densely packed objects. Additionally, we introduce an EM-Merger unit to resolve redundant object detections. Experimental results on the RebarDSC and SKU110K datasets demonstrate that our method significantly outperforms the baseline approach, achieving new state-of-the-art detection performance. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective 39

Revisiting Graph Contrastive Learning on Anomaly Detection: ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Yiming Peng, Zhen Shi, Bin Hua, Xu Dong, Bo Wang, Song Chen, Chen School of Computer Science and Technology Xi'an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China School of Distance Education Xi'an Jiaotong University China University of Virginia Charlottesville VA United States

ISBN: (纸本)157735897X

The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Generalization on Graphs via Progressive Inference

arXiv

引用

arXiv 2025年

作者： Xu, Yiming Shi, Bin Peng, Zhen Liu, Huixiang Dong, Bo Chen, Chen School of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China School of Distance Education Xi’an Jiaotong University China University of Virginia CharlottesvilleVA United States

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%. 1 © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Life Event Tree Generation for Older Adults 1

引用

24th International Conference on Human-Computer Interaction, HCII 2022

作者： Gui, Fang Wu, Xi Hu, Min Yang, Jiaoyun School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

Studies have shown that learning personal stories could help provide individualized eldercare services. However, personal stories are often disordered because of the scattered collection, including informal interviews or daily interactions, which brings difficulties in acquiring valuable information quickly. One solution to this problem is to extract events from personal stories and automatically organize them in chronological order. Events extracted by current methods from social media or news corpus are mainly organized in a linear structure. These works usually focus on the event time and ignore the consistency of event contents when organizing events. This paper aims to organize events into a tree structure based on an event network, with stem nodes representing key event topics and branch nodes representing detailed events. Social workers or caregivers can clarify the life experience of the older adults quickly through the event tree and have a preliminary understanding of them. The experiments show that the event tree generated by our method has a better performance in consistency than current event organization methods. A survey study shows that our method achieves the highest logical coherence for the event tree branches compared with other algorithms. © 2022, Springer Nature Switzerland AG.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

MODFuzz: A Multi-Objective Directed Fuzzer for USB Drivers

引用

IEEE Internet of Things Journal 2025年第12期12卷 21364-21378页

作者： Zhou, Yilin Peng, Guojun Wang, Xingliang Wang, Chenyang Li, Zichuan Liu, Side Wang, Yanhao Yang, Xiuzhang Fu, Jianming Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Indiana University Bloomington BloomingtonIN United States Nio Inc Beijing China Guizhou University Guizhou Big Data Academy Guiyang China

USB interfaces have become ubiquitous in various Internet of Things (IoT) devices, all adhering to the same USB protocol. While enhancing convenience, they also widen the potential attack surface. Fuzzing is a proactive way to identify potential security threats for USB drivers. However, existing USB driver fuzzers primarily prioritize the code coverage of USB drivers, leading to a significant waste of computational resources on irrelevant code segments. To this end, we combine directed fuzzing and USB driver fuzzing for the first time, and present MODFuzz, a pioneering multi-objective directed fuzzing method for USB drivers. MODFuzz autonomously locates the most vulnerable parts within USB drivers, concentrating fuzzing efforts on these areas. Diverging from the existing directed fuzzers, MODFuzz employs a dynamic direction instead of predetermined addresses to guide the fuzzing campaign toward the triggered execution traces with a greater probability of containing vulnerabilities. MODFuzz outperforms the strong baseline in terms of execution speed (about 14% improvement) and crash generation capabilities (about 69% improvement). Meanwhile, we found six previously unknown bugs (all confirmed and assigned vulnerability IDs) in Linux kernel v6.4.10 and received acknowledgment from Red Hat. © 2025 IEEE.

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

A resilient generative model in few-shot question answering

引用

knowledge-Based Systems 2025年 323卷

作者： Zou, Anqi Chen, Yanping Huang, Ruizhang Qin, Yongbin Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang Guizhou550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang Guizhou550025 China College of Computer Science and Technology Guizhou University Guiyang550025 China

In few-shot question answering (QA), only a limited number of training cases are available to tune pre-trained language models (PLMs) for fitting to the task objective. Because a PLM often contains a large number of parameters optimized by a pretraining objective, it is difficult to bridge the gap between the two optimization objectives with a few training cases, which leads to the overfitting problem. Furthermore, in the decoding process of a generative model, sometimes rebuilding an answer to a question is more challenging than directly choosing from an input, because the ability to rebuild requires more informative knowledge and may generate hallucinatory outputs. Motivated by the above discussions, we propose a resilient deep model to support the few-shot question answering tasks. Instead of ambitiously optimizing a full generative model with a few training cases, the resilient model contains a partial learning module and an answer choosing module to reduce the problems caused by a lack of training cases. This has the advantage to enhance the few-shot learning in question answering. Our method was evaluated using several few-shot QA public evaluation datasets. It achieves a state-of-the-art performance, considerably outperforming related works. © 2025 Elsevier B.V.

关键词： Answer choosing Few-shot question answering Overfitting Partial learning The resilient model

来源：评论

学校读者我要写书评

暂无评论

TFGDA: exploring topology and feature alignment in semi-supervised graph domain adaptation through robust clustering 24

TFGDA: exploring topology and feature alignment in semi-supe...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jun Dan Weiming Liu Chunfeng Xie Hua Yu Shunjie Dong Yanchao Tan Zhejiang University Queen Mary University of London Dalian University of Technology Shanghai Jiao Tong University Fuzhou University and Engineering Research Center of Big Data Intelligence Ministry of Education and Fujian Key Laboratory of Network Computing and Intelligent Information Processing

ISBN: (纸本)9798331314385

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods.

关键词：

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：