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

Membership Inference Attacks Against Sequential Recommender Systems 23

Membership Inference Attacks Against Sequential Recommender ...

引用

32nd ACM World Wide Web Conference, WWW 2023

作者： Zhu, Zhihao Wu, Chenwang Fan, Rui Lian, Defu Chen, Enhong School of Data Science University of Science and Technology of China Hefei China School of Computer Science University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9781450394161

Recent studies have demonstrated the vulnerability of recommender systems to membership inference attacks, which determine whether a user's historical data was utilized for model training, posing serious privacy leakage issues. Existing works assumed that member and non-member users follow different recommendation modes, and then infer membership based on the difference vector between the user's historical behaviors and the recommendation list. The previous frameworks are invalid against inductive recommendations, such as sequential recommendations, since the disparities of difference vectors constructed by the recommendations between members and non-members become imperceptible. This motivates us to dig deeper into the target model. In addition, most MIA frameworks assume that they can obtain some in-distribution data from the same distribution of the target data, which is hard to gain in recommender system. To address these difficulties, we propose a Membership Inference Attack framework against sequential recommenders based on Model Extraction(ME-MIA). Specifically, we train a surrogate model to simulate the target model based on two universal loss functions. For a given behavior sequence, the loss functions ensure the recommended items and corresponding rank of the surrogate model are consistent with the target model's recommendation. Due to the special training mode of the surrogate model, it is hard to judge which user is its member(non-member). Therefore, we establish a shadow model and use shadow model's members(non-members) to train the attack model later. Next, we build a user feature generator to construct representative feature vectors from the shadow(surrogate) model. The crafting feature vectors are finally input into the attack model to identify users' membership. Furthermore, to tackle the high cost of obtaining in-distribution data, we develop two variants of ME-MIA, realizing data-efficient and even data-free MIA by fabricating authentic in-distrib

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Differentiable Optimized Product Quantization and Beyond 23

Differentiable Optimized Product Quantization and Beyond

引用

32nd ACM World Wide Web Conference, WWW 2023

作者： Lu, Zepu Lian, Defu Zhang, Jin Zhang, Zaixi Feng, Chao Wang, Hao Chen, Enhong School of Computer Science University of Science and Technology of China Hefei China School of Data Science University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Hefei China

ISBN: (纸本)9781450394161

Vector quantization techniques, such as Product Quantization (PQ), play a vital role in approximate nearest neighbor search (ANNs) and maximum inner product search (MIPS) owing to their remarkable search and storage efficiency. However, the indexes in vector quantization cannot be trained together with the inference models since data indexing is not differentiable. To this end, differentiable vector quantization approaches, such as DiffPQ and DeepPQ, have been recently proposed, but existing methods have two drawbacks. First, they do not impose any constraints on codebooks, such that the resultant codebooks lack diversity, leading to limited retrieval performance. Second, since data indexing resorts to operator, differentiability is usually achieved by either relaxation or Straight-Through Estimation (STE), which leads to biased gradient and slow convergence. To address these problems, we propose a Differentiable Optimized Product Quantization method (DOPQ) and beyond in this paper. Particularly, each data is projected into multiple orthogonal spaces, to generate multiple views of data. Thus, each codebook is learned with one view of data, guaranteeing the diversity of codebooks. Moreover, instead of simple differentiable relaxation, DOPQ optimizes the loss based on direct loss minimization, significantly reducing the gradient bias problem. Finally, DOPQ is evaluated with seven datasets of both recommendation and image search tasks. Extensive experimental results show that DOPQ outperforms state-of-the-art baselines by a large margin. © 2023 ACM.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Generative Multimodal data Augmentation for Low-Resource Multimodal Named Entity Recognition 24

Generative Multimodal Data Augmentation for Low-Resource Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Ziyan Yu, Jianfei Yang, Jia Wang, Wenya Yang, Li Xia, Rui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China College of Computing and Data Science Nanyang Technological University Singapore Wee Kim Wee School of Communication and Information Nanyang Technological University Singapore

ISBN: (纸本)9798400706868

As an important task in multimodal information extraction, Multimodal Named Entity Recognition (MNER) has recently attracted considerable attention. One key challenge of MNER lies in the lack of sufficient fine-grained annotated data, especially in low-resource scenarios. Although data augmentation is a widely used technique to tackle the above issue, it is challenging to simultaneously generate synthetic text-image pairs and their corresponding high-quality entity annotations. In this work, we propose a novel Generative Multimodal data Augmentation (GMDA) framework for MNER, which contains two stages: Multimodal Text Generation and Multimodal Image Generation. Specifically, we first transform each annotated sentence into a linearized labeled sequence, and then train a Label-aware Multimodal Large Language Model (LMLLM) to generate the labeled sequence based on a label-aware prompt and its associated image. We further employ a Stable Diffusion model to generate the synthetic images that are semantically related to these sentences. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed GMDA framework, which consistently boosts the performance of several competitive methods for two subtasks of MNER in both full-supervision and low-resource settings. The low-resource dataset and source code are released at https://***/NUSTM/GMDA. © 2024 ACM.

关键词： data augmentation

来源：评论

学校读者我要写书评

暂无评论

OOCDB:A Comprehensive,Systematic,and Real-time Organs-on-a-chip database

引用

Genomics, Proteomics & Bioinformatics 2023年第2期21卷 243-258页

作者： Jian Li Weicheng Liang Zaozao Chen Xingyu Li Pan Gu Anna Liu Pin Chen Qiwei Li Xueyin Mei Jing Yang Jun Liu Lincao Jiang Zhongze Gu School of Life Science and Technology Southeast UniversityNanjing 210096China School of Biological Science&Medical Engineering Southeast UniversityNanjing 210096China School of Computer Data&Information SciencesUniversity of Wisconsin-MadisonMadisonWI 53706USA

Organs-on-a-chip is a microfluidic microphysiological system that uses microfluidic technology to analyze the structure and function of living human cells at the tissue and organ levels in ***-on-a-chip technology,as opposed to traditional two-dimensional cell culture and animal models,can more closely simulate pathologic and toxicologic interactions between different organs or tissues and reflect the collaborative response of multiple organs to *** the fact that many organs-on-a-chip-related data have been published,none of the current databases have all of the following functions:searching,downloading,as well as analyzing data and results from the literature on ***,we created an organs-on-a-chip database(OOCDB)as a platform to integrate information about organs-on-a-chip from various sources,including literature,patents,raw data from microarray and transcriptome sequencing,several open-access datasets of organs-on-a-chip and organoids,and data generated in our *** contains dozens of sub-databases and analysis tools,and each sub-database contains various data associated with organs-on-a-chip,with the goal of providing researchers with a comprehensive,systematic,and convenient search ***,it offers a variety of other functions,such as mathematical modeling,three-dimensional modeling,and citation mapping,to meet the needs of organs-on-a-chip.

关键词： Organ Mathematical model Citation map Organs-on-a-chip

来源：评论

学校读者我要写书评

暂无评论

ICL: Iterative Continual Learning for Multi-domain Neural Machine Translation

ICL: Iterative Continual Learning for Multi-domain Neural Ma...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Man, Zhibo Huang, Kaiyu Zhang, Yujie Chen, Yuanmeng Chen, Yufeng Xu, Jinan Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science and Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798891761681

In a practical scenario, multi-domain neural machine translation (MDNMT) aims to continuously acquire knowledge from new domain data while retaining old *** work separately learns each new domain knowledge based on parameter isolation methods, which effectively capture the new ***, task-specific parameters lead to isolation between models, which hinders the mutual transfer of knowledge between new *** the scarcity of domain-specific corpora, we consider making full use of the data from multiple new ***, our work aims to leverage previously acquired domain knowledge when modeling subsequent *** this end, we propose an Iterative Continual Learning (ICL) framework for multi-domain neural machine ***, when each new domain arrives, (1) we first build a pluggable incremental learning model, (2) then we design an iterative updating algorithm to continuously update the original model, which can be used flexibly for constructing subsequent domain ***, we design a domain knowledge transfer mechanism to enhance the fine-grained domain-specific representation, thereby solving the word ambiguity caused by mixing domain *** results on the UM-Corpus and OPUS multi-domain datasets show the superior performance of our proposed model compared to representative baselines. © 2024 Association for Computational Linguistics.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

On the Effect of Cross-Channel Normalization on Wide-Shallow Convolutional Networks 26

On the Effect of Cross-Channel Normalization on Wide-Shallow...

引用

26th Irish Machine Vision and Image Processing Conference, IMVIP 2024

作者： Alakkari, Salaheddin Mileo, Alessandra Department of Computer Science and Information Systems University of Limerick Ireland Insight Centre for Data Analytics Dublin City University Ireland

ISBN: (纸本)9781837242672

Cross-channel Normalization (CN) was first proposed in AlexNet paper as a biologically inspired normalization process mimicking the lateral inhibition phenomenon in biological neurons. However, the effect of such a normalization was not well explored in the literature due to the wide popularity of batch normalization. In this paper, we show that such a type of normalization can significantly enhance the network accuracy when applied to wide-shallow convolutional networks. Wide-shallow networks are more advantageous compared to deep CNNs since they significantly increase parallelism and reduce the sequential computation across layers. Our experiments show that using cross-channel normalization not only improves the accuracy of residual and standard convolutional networks on benchmark datasets but also significantly enhances the performance when considering limited and reduced representation examples. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Graph Attention Network-based Multimodal Fusion for Fake Food Reviews Detection 24

Graph Attention Network-based Multimodal Fusion for Fake Foo...

引用

9th International Conference on Cyber Security and Information Engineering, ICCSIE 2024

作者： Yang, Jiajie Mao, Dianhui Zhang, Denghui Beijing Key Laboratory of Big Data Technology for Food Safety Computer Science Department Beijing Technology and Business University China

ISBN: (纸本)9798400718137

In the field of computational intelligence and data analytics, the detection of fake food reviews has emerged as a pressing challenge, exacerbated by the widespread use of social media. These fraudulent reviews, particularly prevalent in the food and beverage industry, distort consumer decision-making and disrupt market fairness. To address this, we propose GMF-R, an innovative multimodal fusion framework based on Graph Attention Network (GAT), designed to effectively detect fake food reviews. The framework features end-to-end trainability and introduces advanced multimodal feature processing mechanisms, including fine-grained cross-modal interactions, a shared feature space, and multimodal graph construction. By utilizing GAT, GMF-R can adaptively assign attention weights to key nodes and accurately capture complex inter-modal relationships. Experimental results demonstrate that GMF-R achieves a 97.4% accuracy rate and a 98.1% F1 score on the Yelp reviews website dataset, significantly outperforming previous state-of-the-art models. © 2024 Copyright held by the owner/author(s).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

PCBERT: Parent and Child BERT for Chinese Few-shot NER 29

PCBERT: Parent and Child BERT for Chinese Few-shot NER

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Lai, Peichao Ye, Feiyang Zhang, Lin Chen, Zhiwei Fu, Yanggeng Wu, Yingjie Wang, Yilei College of Computer and Data Science Fuzhou University China

Achieving good performance on few-shot or zero-shot datasets has been a long-term challenge for NER. The conventional semantic transfer approaches on NER will decrease model performance when the semantic distribution is quite different, especially in Chinese few-shot NER. Recently, prompt-tuning has been thoroughly considered for low-resource tasks. But there is no effective prompt-tuning approach for Chinese few-shot NER. In this work, we propose a prompt-based Parent and Child BERT (PCBERT) for Chinese few-shot NER. To train an annotating model on high-resource datasets and then discover more implicit labels on low-resource datasets. We further design a label extension strategy to achieve label transferring from high-resource datasets. We evaluated our model on Weibo and the other three sampling Chinese NER datasets, and the experimental result demonstrates our approach’s effectiveness in few-shot learning. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SpeAr: A Spectral Approach for Zero-Shot Node Classification 38

SpeAr: A Spectral Approach for Zero-Shot Node Classification

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Ting Wang, Da Liang, Jiye Zhang, Kaihan Zeng, Jianchao Data Science and Technology North University of China Taiyuan China School of Computer and Information Technology Shanxi University Taiyuan China

Zero-shot node classification is a vital task in the field of graph data processing, aiming to identify nodes of classes unseen during the training process. Prediction bias is one of the primary challenges in zero-shot node classification, referring to the model's propensity to misclassify nodes of unseen classes as seen classes. However, most methods introduce external knowledge to mitigate the bias, inadequately leveraging the inherent cluster information within the unlabeled nodes. To address this issue, we employ spectral analysis coupled with learnable class prototypes to discover the implicit cluster structures within the graph, providing a more comprehensive understanding of classes. In this paper, we propose a Spectral Approach for zero-shot node classification (SpeAr). Specifically, we establish an approximate relationship between minimizing the spectral contrastive loss and performing spectral decomposition on the graph, thereby enabling effective node characterization through loss minimization. Subsequently, the class prototypes are iteratively refined based on the learned node representations, initialized with the semantic vectors. Finally, extensive experiments verify the effectiveness of the SpeAr, which can further alleviate the bias problem. © 2024 Neural information processing systems foundation. All rights reserved.

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：