检索结果-内蒙古大学图书馆

Unsupervised Social Bot Detection via Structural Information Theory

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Peng, Hao Zhang, Jingyun Huang, Xiang Hao, Zhifeng Li, Angsheng Yu, Zhengtao Yu, Philip S. School of Cyber Science and Technology Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China State Key Laboratory of Public Big Data Guizhou University No. 2708 South Section of Huaxi Avenue Huaxi District Guizhou Province Guiyang City550025 China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China College of Science University of Shantou No. 243 University Road Shantou515063 China School of Computer Science and Engineering Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China Faculty of Information Engineering and Automation Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

Research on social bot detection plays a crucial role in maintaining the order and reliability of information dissemination while increasing trust in social interactions. The current mainstream social bot detection models rely on black-box neural network technology, e.g., Graph Neural Network, Transformer, etc., which lacks interpretability. In this work, we present UnDBot, a novel unsupervised, interpretable, yet effective and practical framework for detecting social bots. This framework is built upon structural information theory. We begin by designing three social relationship metrics that capture various aspects of social bot behaviors: Posting Type Distribution, Posting Influence, and Follow-to-follower Ratio. Three new relationships are utilized to construct a new, unified, and weighted social multi-relational graph, aiming to model the relevance of social user behaviors and discover long-distance correlations between users. Second, we introduce a novel method for optimizing heterogeneous structural entropy. This method involves the personalized aggregation of edge information from the social multi-relational graph to generate a two-dimensional encoding tree. The heterogeneous structural entropy facilitates decoding of the substantial structure of the social bots network and enables hierarchical clustering of social bots. Thirdly, a new community labeling method is presented to distinguish social bot communities by computing the user's stationary distribution, measuring user contributions to network structure, and counting the intensity of user aggregation within the community. Compared with ten representative social bot detection approaches, comprehensive experiments demonstrate the advantages of effectiveness and interpretability of UnDBot on four real social network datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Information theory

Equivariant spatio-temporal attentive graph networks to simulate physical dynamics 23

学校读者我要写书评

暂无评论

Equivariant spatio-temporal attentive graph networks to simu...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Liming Wu Zhichao Hou Jirui Yuan Yu Rong Wenbing Huang Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science North Carolina State University Institute for AI Industry Research (AIR) Tsinghua University Tencent AI Lab

Learning to represent and simulate the dynamics of physical systems is a crucial yet challenging task. Existing equivariant Graph Neural Network (GNN) based methods have encapsulated the symmetry of physics, e.g., translations, rotations, etc, leading to better generalization ability. Nevertheless, their frame-to-frame formulation of the task overlooks the non-Markov property mainly incurred by unobserved dynamics in the environment. In this paper, we reformulate dynamics simulation as a spatio-temporal prediction task, by employing the trajectory in the past period to recover the Non-Markovian interactions. We propose Equivariant Spatio-Temporal Attentive Graph Networks (ESTAG), an equivariant version of spatio-temporal GNNs, to fulfill our purpose. At its core, we design a novel Equivariant Discrete Fourier Transform (EDFT) to extract periodic patterns from the history frames, and then construct an Equivariant Spatial Module (ESM) to accomplish spatial message passing, and an Equivariant Temporal Module (ETM) with the forward attention and equivariant pooling mechanisms to aggregate temporal message. We evaluate our model on three real datasets corresponding to the molecular-, protein- and macro-level. Experimental results verify the effectiveness of ESTAG compared to typical spatio-temporal GNNs and equivariant GNNs.

关键词：

AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Chaohu Gui, Tianyi Liu, Yu Xu, Linli School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tongyi Lab China

Large Vision-Language Models (LVLMs), such as GPT-4o and LLaVA, have recently witnessed remarkable advancements and are increasingly being deployed in real-world applications. However, inheriting the sensitivity of visual neural networks, LVLMs remain vulnerable to adversarial attacks, which can result in erroneous or malicious outputs. While existing efforts utilize adversarial fine-tuning to enhance robustness, they often suffer from performance degradation on clean inputs. In this paper, we proposes AdPO, a novel adversarial defense strategy for LVLMs based on preference optimization. For the first time, we reframe adversarial training as a preference optimization problem, aiming to enhance the model’s preference for generating normal outputs on clean inputs while rejecting the potential misleading outputs for adversarial examples. Notably, AdPO achieves this by solely modifying the image encoder, e.g., CLIP ViT, resulting in superior clean and adversarial performance in a variety of downsream tasks. Considering that training involves large language models (LLMs), the computational cost increases significantly. We validate that training on smaller LVLMs and subsequently transferring to larger models can achieve competitive performance while maintaining efficiency comparable to baseline methods. Our comprehensive experiments confirm the effectiveness of the proposed AdPO, which provides a novel perspective for future adversarial defense research. Copyright © 2025, The Authors. All rights reserved.

关键词：

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-label Classification of CLIP Without Training

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Yuqi Chen, Minghao Zhang, Kaipeng Li, Hengjia Li, Mingming Yang, Zheng Lv, Dongqin Lin, Binbin Liu, Haifeng Cai, Deng State Key Lab of CAD&CG College of Computer Science Zhejiang University China Hangzhou Dianzi University China Shanghai Artificial Intelligence Laboratory China FABU Inc. School of Software Technology Zhejiang University China Nantong Port Group China

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text descriptions supervised by contrastive loss, making it highly effective for single-label classification. However, it shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class and the contrastive nature of softmax operation aggravates it. In this study, we observe that the multi-label classification results heavily rely on discriminative local features but are overlooked by CLIP. As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags. It comprises three steps: (1) patch-level classification to obtain coarse scores;(2) dual-masking attention refinement (DMAR) module to refine the coarse scores;(3) class-wise reidentification (CWR) module to remedy predictions from a global perspective. This framework is solely based on frozen CLIP and significantly enhances its multi-label classification performance on various benchmarks without dataset-specific training. Besides, to comprehensively assess the quality and practicality of generated tags, we extend their application to the downstream task, i.e., weakly supervised semantic segmentation (WSSS) with generated tags as image-level pseudo labels. Experiments demonstrate that this classify-then-segment paradigm dramatically outperforms other annotation-free segmentation methods and validates the effectiveness of generated tags. Our code is available at https://***/linyq2117/TagCLIP. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY labELS 9

学校读者我要写书评

暂无评论

ROBUST EARLY-LEARNING: HINDERING THE MEMORIZATION OF NOISY L...

9th International Conference on Learning Representations, ICLR 2021

作者： Xia, Xiaobo Liu, Tongliang Han, Bo Gong, Chen Wang, Nannan Ge, Zongyuan Chang, Yi Trustworthy Machine Learning Lab School of Computer Science The University of Sydney Australia Department of Computer Science Hong Kong Baptist University Hong Kong School of Computer Science and Engineering Nanjing University of Science and Technology China ISN State Key Laboratory School of Telecommunications Engineering Xidian University China Medical AI Group Faculty of Engineering Monash University Australia Airdoc Research Monash University Australia School of Artificial Intelligence Jilin University China

The memorization effects of deep networks show that they will first memorize training data with clean labels and then those with noisy labels. The early stopping method therefore can be exploited for learning with noisy labels. However, the side effect brought by noisy labels will influence the memorization of clean labels before early stopping. In this paper, motivated by the lottery ticket hypothesis which shows that only partial parameters are important for generalization, we find that only partial parameters are important for fitting clean labels and generalize well, which we term as critical parameters;while the other parameters tend to fit noisy labels and cannot generalize well, which we term as non-critical parameters. Based on this, we propose robust early-learning to reduce the side effect of noisy labels before early stopping and thus enhance the memorization of clean labels. Specifically, in each iteration, we divide all parameters into the critical and non-critical ones, and then perform different update rules for different types of parameters. Extensive experiments on benchmark-simulated and real-world label-noise datasets demonstrate the superiority of the proposed method over the state-of-the-art label-noise learning methods. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Iterative methods

IC CLASSIFIER: A CLASSIFIER FOR 3D INDUSTRIAL COMPONENTS BASED ON GEOMETRIC PRIOR USING GNN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Zipeng Nie, Zhenguo University of California Berkeley United States Computer Science division UC Berkeley United States Department of Mechanical Engineering Tsinghua University Beijing100084 China State Key Laboratory of Tribology in Advanced Equipment Beijing100084 China Beijing Key Lab of Precision/Ultra-precision Manufacturing Equipments and Control Beijing100084 China

In this paper, we propose an approach to address the problem of classifying 3D industrial components by introducing a novel framework named IC-classifier (Industrial Component classifier). Our framework is designed to focus on the object’s local and global structures, emphasizing the former by incorporating specific local features for embedding the model. By utilizing graphical neural networks and embedding derived from geometric properties, IC-classifier facilitates the exploration of the local structures of the object while using geometric attention for the analysis of global structures. Furthermore, the framework uses point clouds to circumvent the heavy computation workload. The proposed framework’s performance is benchmarked against state-of-the-art models, demonstrating its potential to compete in the field. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

ToPoFM: Topology-Guided Pathology Foundation Model for High-Resolution Pathology Image Synthesis with Cellular-Level Control

学校读者我要写书评

暂无评论

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Li, Jingxiong Zhu, Chenglu Zheng, Sunyi Chen, Pingyi Sun, Yuxuan Li, Honglin Yang, Lin Zhejiang University College of Computer Science and Technology Hangzhou310027 China Westlake University School of Engineering Hangzhou310024 China Tianjin Medical University Cancer Institute and Hospital National Clinical Research Center for Cancer Tianjin's Clinical Research Center for Cancer State Key Laboratory of Druggability Evaluation and Systematic Translational Medicine Tianjin Key Laboratory of Digestive Cancer Key Laboratory of Cancer Prevention and Therapy Department of Radiology Tianjin China Westlake University Artificial Intelligence and Biomedical Image Analysis Lab School of Engineering Hangzhou310024 China Westlake Institute for Advanced Study Institute of Advanced Technology Hangzhou310024 China Muyuan Laboratory Center for Interdisciplinary Research and Innovation Henan Zhengzhou450016 China

Synthetic data generation emerges as a strategy to mitigate data scarcity in digital pathology, where complicated tissue and cellular features are correlated with cancer diagnosis. The synthesis of such visuals, however, suffers from limited inter class diversity and scarcity of cellular annotations. Current methodologies struggle with capturing the broad spectrum of pathology features, causing unpredictable objects and defected fidelity. Moreover, discrepancies in image resolution across developmental and operational phases can amplify the distribution shifts, undermining the precision of diagnosis. To address these challenges, we introduce TOpology guided PathOlogy Foundation Model (ToPoFM), a visual foundation model designed for the synthesis of high-resolution pathology images with cellular-level control. Our approach integrates a topology-informed cell arrangement generator to steer large language models for crafting synthetic cell arrangements. We correlate cell arrangement guidance with diffusion model for pathology content generation, then further implement a random sliding inference strategy, merging discrete low-resolution samplings into single high-resolution representation. Our model requires only small patches for training. The efficacy of ToPoFM is demonstrated through extensive experiments, complemented by expert validations, showing high fidelity on data synthesis. Additionally, we underscore the utility of our generated imagery as an augmentation tool, enhancing the performance of downstream tasks, including cancer subtype classification and segmentation. © 2025 IEEE.

关键词： Image segmentation

Non-Hermitian Chiral Heat Transport

学校读者我要写书评

暂无评论

Physical Review Letters 2023年第26期130卷 266303-266303页

作者： Guoqiang Xu Xue Zhou Ying Li Qitao Cao Weijin Chen Yunfeng Xiao Lan Yang Cheng-Wei Qiu Department of Electrical and Computer Engineering National University of Singapore Kent Ridge 117583 Republic of Singapore School of Computer Science and Information Engineering Chongqing Technology and Business University Chongqing 400067 China Interdisciplinary Center for Quantum Information State Key Laboratory of Extreme Photonics and Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou 310027 China International Joint Innovation Center Key Lab of Advanced Micro/Nano Electronic Devices and Smart Systems of Zhejiang The Electromagnetics Academy at Zhejiang University Zhejiang University Haining 314400 China State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics School of Physics Peking University100871 Beijing China Department of Electrical and Systems Engineering Washington University St. Louis Missouri 63130 USA

Exceptional point (EP) has been captivated as a concept of interpreting eigenvalue degeneracy and eigenstate exchange in non-Hermitian physics. The chirality in the vicinity of EP is intrinsically preserved and usually immune to external bias or perturbation, resulting in the robustness of asymmetric backscattering and directional emission in classical wave fields. Despite recent progress in non-Hermitian thermal diffusion, all state-of-the-art approaches fail to exhibit chiral states or directional robustness in heat transport. Here we report the first discovery of chiral heat transport, which is manifested only in the vicinity of EP but suppressed at the EP of a thermal system. The chiral heat transport demonstrates significant robustness against drastically varying advections and thermal perturbations imposed. Our results reveal the chirality in heat transport process and provide a novel strategy for manipulating mass, charge, and diffusive light.

关键词： Diffusion Heat transfer Metamaterials Non-Hermitean systems

Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Points

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hou, Fei Wang, Chiyu Wang, Wencheng Qin, Hong Qian, Chen He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Department of Computer Science Stony Brook University New York United States SenseTime Research Tetras.AI Beijing China School of Computer Science and Engineering S-Lab Nanyang Technological University Singapore

Poisson surface reconstruction (PSR) remains a popular technique for reconstructing watertight surfaces from 3D point samples thanks to its efficiency, simplicity, and robustness. Yet, the existing PSR method and subsequent variants work only for oriented points. This paper intends to validate that an improved PSR, called iPSR, can completely eliminate the requirement of point normals and proceed in an iterative manner. In each iteration, iPSR takes as input point samples with normals directly computed from the surface obtained in the preceding iteration, and then generates a new surface with better quality. Extensive quantitative evaluation confirms that the new iPSR algorithm converges in 5-30 iterations even with randomly initialized normals. If initialized with a simple visibility based heuristic, iPSR can further reduce the number of iterations. We conduct comprehensive comparisons with PSR and other powerful implicit-function based methods. Finally, we confirm iPSR's effectiveness and scalability on the AIM@SHAPE dataset and challenging (indoor and outdoor) scenes. Code and data for this paper are at https://***/houfei0801/ipsr. © 2022, CC BY-NC-SA.

关键词： Iterative methods