检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Zhang, Zheng Liu, Qi Hu, Zirui Zhan, Yi Huang, Zhenya Gao, Weibo Mao, Qingyang School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China School of Data Science University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China School of Computer Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9798400701719

Meta-learning has been widely employed to tackle the cold-start problem in user modeling. Similar to a guidebook for a new traveler, meta-learning significantly affects decision-making for new users in crucial scenarios, such as career recommendations. Consequently, the issue of fairness in meta-learning has gained paramount importance. Several methods have been proposed to mitigate unfairness in meta-learning and have shown promising results. However, a fundamental question remains unexplored: What is the critical factor leading to unfairness in meta-learned user modeling? Through the theoretical analysis that integrates the meta-learning paradigm with group fairness metrics, we identify group proportion imbalance as a critical factor. Subsequently, in order to mitigate the impact of this factor, we introduce a novel Fairness-aware Adaptive Sampling framework for meTa-learning, abbreviated as FAST. Its core concept involves adaptively adjusting the sampling distribution for different user groups during the interleaved training process of meta-learning. Furthermore, we provide theoretical guarantees demonstrating the convergence of FAST. Finally, empirical experiments conducted on three datasets reveal that FAST effectively enhances fairness while maintaining high accuracy. The code for FAST is available at https://***/zhengz99/FAST. © 2024 Owner/Author.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

Science China(Information Sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking 37

AdaptSSR: Pre-training User Model with Augmentation-Adaptive...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Yu, Yang Liu, Qi Zhang, Kai Zhang, Yuren Song, Chao Hou, Min Yuan, Yuqing Ye, Zhihao Zhang, Zaixi Yu, Sanshi Lei Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China OPPO Research Institute China Hefei University of Technology China

ISBN: (纸本)9781713899921

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on massive user behavior sequences with a contrastive learning task. Generally, these methods assume different views of the same behavior sequence constructed via data augmentation are semantically consistent, i.e., reflecting similar characteristics or interests of the user, and thus maximizing their agreement in the feature space. However, due to the diverse interests and heavy noise in user behaviors, existing augmentation methods tend to lose certain characteristics of the user or introduce noisy behaviors. Thus, forcing the user model to directly maximize the similarity between the augmented views may result in a negative transfer. To this end, we propose to replace the contrastive learning task with a new pretext task: Augmentation-Adaptive Self-Supervised Ranking (AdaptSSR), which alleviates the requirement of semantic consistency between the augmented views while pre-training a discriminative user model. Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users. We further employ an in-batch hard negative sampling strategy to facilitate model training. Moreover, considering the distinct impacts of data augmentation on different behavior sequences, we design an augmentation-adaptive fusion mechanism to automatically adjust the similarity order constraint applied to each sample based on the estimated similarity between the augmented views. Extensive experiments on both public and industrial datasets with six downstream tasks verify the effectiveness of AdaptSSR. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multimodal Biological Knowledge Graph Completion via Triple Co-Attention Mechanism 39

Multimodal Biological Knowledge Graph Completion via Triple ...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Xu, Derong Zhou, Jingbo Xu, Tong Xia, Yuan Liu, Ji Chen, Enhong Dou, Dejing University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Baidu Research Business Intelligence Lab Baidu Intelligent Healthcare Unit Baidu Research Big Data Lab BCG X

ISBN: (纸本)9798350322279

Biological Knowledge Graphs (BKGs) can help to model complex biological systems in a structural way to support various tasks. Nevertheless, the incompleteness problem may limit the performance of existing BKGs, which still deserves new methods to reveal the missing relations. Though great efforts have been made to knowledge graph completion, existing methods are not easy to be adapted to the multimodal biological information such as molecular structures and textual descriptions. To this end, we propose a novel co-attention-based multimodal embedding framework, named CamE, for the multimodal BKG completion task. Specifically, we design a Triple Co-Attention (TCA) operator to capture and highlight the same semantic features among different modalities. Based on TCA, we further propose two components to handle multimodal fusion and multimodal entity-relation interaction, respectively. One is the multimodal TCA fusion module to achieve a multimodal joint representation for each entity in the BKG. It aims to project different modal information into a common space by capturing the same semantic features and overcoming the modality gap. The other is the relation-aware interactive TCA module to learn interactive representation by modelling the deep interaction between multimodal entities and relations. Extensive experiments on two real-world multimodal BKG datasets demonstrate that our method significantly outperforms several state-of-the-art baselines, including 10.3% and 16.2% improvement w.r.t MRR and Hits@1 metrics over its best competitors on public DRKG-MM dataset. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

MassNE: Exploring Higher-Order Interactions with Marginal Effect for Massive Battle Outcome Prediction 23

MassNE: Exploring Higher-Order Interactions with Marginal Ef...

引用

2023 World Wide Web Conference, WWW 2023

作者： Gu, Yin Zhang, Kai Liu, Qi Lin, Xin Huang, Zhenya Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9781450394161

In online games, predicting massive battle outcomes is a fundamental task of many applications, such as team optimization and tactical formulation. Existing works do not pay adequate attention to the massive battle. They either seek to evaluate individuals in isolation or mine simple pair-wise interactions between individuals, neither of which effectively captures the intricate interactions between massive units (e.g., individuals). Furthermore, as the team size increases, the phenomenon of diminishing marginal utility of units emerges. Such a diminishing pattern is rarely noticed in previous work, and how to capture it from data remains a challenge. To this end, we propose a novel Massive battle outcome predictor with margiNal Effect modules, namely MassNE, which comprehensively incorporates individual effects, cooperation effects (i.e., intra-team interactions) and suppression effects (i.e., inter-team interactions) for predicting battle outcomes. Specifically, we design marginal effect modules to learn how units' marginal utility changing respect to their number, where the monotonicity assumption is applied to ensure rationality. In addition, we evaluate the current classical models and provide mathematical proofs that MassNE is able to generalize several earlier works in massive settings. Massive battle datasets generated by StarCraft II APIs are adopted to evaluate the performances of MassNE. Extensive experiments empirically demonstrate the effectiveness of MassNE, and MassNE can reveal reasonable cooperation effects, suppression effects, and marginal utilities of combat units from the data. © 2023 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Sparse representation scheme with enhanced medium pixel intensity for face recognition

引用

CAAI Transactions on intelligence technology 2024年第1期9卷 116-127页

作者： Xuexue Zhang Yongjun Zhang Zewei Wang Wei Long Weihao Gao Bob Zhang State Key Laboratory of Public Big Data Institute for Artificial IntelligenceCollege of Computer Science and TechnologyGuizhou UniversityGuiyangGuizhouChina Department of Computer and Information Science University of MacaoAvenida da UniversidadeTaipaMacaoChina

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test *** has been widely used in various image classification *** in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for *** deformable images such as human faces,pixels at the same location of different images of the same subject usually have different ***,extracting features and correctly classifying such deformable objects is very ***,the lighting,attitude and occlusion cause more *** the problems and challenges listed above,a novel image representation and classification algorithm is ***,the authors’algorithm generates virtual samples by a non-linear variation *** method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable *** combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the ***,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion *** weighting coefficients in the score fusion scheme are set entirely ***,the algorithm classifies the samples based on the final *** experimental results show that our method performs better classification than conventional sparse representation algorithms.

关键词： computer vision face recognition image classification image representation

来源：评论

学校读者我要写书评

暂无评论

Towards privacy-preserving and efficient word vector learning for lightweight IoT devices

引用

Digital Communications and Networks 2024年第4期10卷 895-903页

作者： Nan Jia Shaojing Fu Guangquan Xu Kai Huang Ming Xu National University of Defense Technology ChangshaChina Big Data School Qingdao Huanghai UniversityQingdaoChina Tianjin Key Laboratory of Advanced Networking College of Intelligence and ComputingTianjin UniversityTianjinChina College of Joint Operations National Defense UniversityShijiazhuangChina

Nowadays,Internet of Things(IoT)is widely deployed and brings great opportunities to change people's daily *** realize more effective human-computer interaction in the IoT applications,the Question Answering(QA)systems implanted in the IoT services are supposed to improve the ability to understand natural ***,the distributed representation of words,which contains more semantic or syntactic information,has been playing a more and more important role in the QA ***,learning high-quality distributed word vectors requires lots of storage and computing resources,hence it cannot be deployed on the resource-constrained IoT *** is a good choice to outsource the data and computation to the cloud ***,it could cause privacy risks to directly upload private data to the untrusted ***,realizing the word vector learning process over untrusted cloud servers without privacy leakage is an urgent and challenging *** this paper,we present a novel efficient word vector learning scheme over encrypted *** first design a series of arithmetic computation *** we use two non-colluding cloud servers to implement high-quality word vectors learning over encrypted *** proposed scheme allows us to perform training word vectors on the remote cloud servers while protecting *** analysis and experiments over real data sets demonstrate that our scheme is more secure and efficient than existing privacy-preserving word vector learning schemes.

关键词： Privacy-preserving Word vector learning Secret sharing Internet of things

来源：评论

学校读者我要写书评

暂无评论

A survey on cross-user federated recommendation

引用

Science China(Information Sciences) 2025年第4期68卷 7-32页

作者： Enyue YANG Yudi XIONG Wei YUAN Weike PAN Qiang YANG Zhong MING College of Computer Science and Software Engineering Shenzhen University School of Electrical Engineering and Computer Science The University of Queensland WeBank AI Lab WeBank Department of Computer Science and Engineering Hong Kong University of Science and Technology College of Big Data and Internet Shenzhen Technology University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)

Recommender systems are effective in mitigating information overload, yet the centralized storage of user data raises significant privacy concerns. Cross-user federated recommendation(CUFR) provides a promising distributed paradigm to address these concerns by enabling privacy-preserving recommendations directly on user devices. In this survey, we review and categorize current progress in CUFR, focusing on four key aspects: privacy, security, accuracy, and efficiency. Firstly,we conduct an in-depth privacy analysis, discuss various cases of privacy leakage, and then review recent methods for privacy protection. Secondly, we analyze security concerns and review recent methods for untargeted and targeted *** untargeted attack methods, we categorize them into data poisoning attack methods and parameter poisoning attack methods. For targeted attack methods, we categorize them into user-based methods and item-based methods. Thirdly,we provide an overview of the federated variants of some representative methods, and then review the recent methods for improving accuracy from two categories: data heterogeneity and high-order information. Fourthly, we review recent methods for improving training efficiency from two categories: client sampling and model compression. Finally, we conclude this survey and explore some potential future research topics in CUFR.

关键词： cross-user federated recommendation federated recommendation federated learning recommender systems user privacy

来源：评论

学校读者我要写书评

暂无评论

Time Series Forecasting with Multi-scale Decomposition and Fourier Neural Operators 7

Time Series Forecasting with Multi-scale Decomposition and F...

引用

7th International Conference on Computer Information Science and Application technology, CISAT 2024

作者： Long, Ruiqi Xie, Hongyi Lian, Defu University of Science and Technology of China School of Data Science Hefei China University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9798350375107

Time series forecasting has a wide range of applications in weather forecasting, energy price prediction, and many other fields. However, real-world time series data are often inherently non-stationary, which makes modeling time series data challenging. Existing research methods typically use seasonal-trend decomposition to disentangle time series data, and then leverage Transformer and other model structures to learn complex, evolving temporal ***, we observe that single seasonal-trend decomposition is often insufficient, and time series data exhibit different pattern regularities at different sampling scales. To address this, we propose a novel method that performs multi-scale seasonal-trend decomposition and aggregates features from fine to coarse scales to fully exploit semantic information. Furthermore, we draw inspiration from ensemble learning and employ Fourier neural operator-based backbone networks at different scales, with the predictions from multiple scales aggregated as the final output prediction. Extensive experiments demonstrate that our proposed model achieves superior prediction performance than state-of-the-art models on multiple public datasets. © 2024 IEEE.

关键词： Prediction models

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：