检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Hengran Tang, Minghao Bi, Keping Guo, Jiafeng Liu, Shihao Shi, Daiting Yin, Dawei Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China Baidu Inc Beijing China Nankai University Tianjin China

Retrieval models typically rely on costly human-labeled query-document relevance annotations for training and evaluation. To reduce this cost and leverage the potential of Large Language Models (LLMs) in relevance judgments, we aim to explore whether LLM-generated annotations can effectively replace human annotations in training retrieval models. Retrieval usually emphasizes relevance, which indicates "topic-relatedness" of a document to a query, while in RAG, the value of a document (or utility), depends on how it contributes to answer generation. Recognizing this mismatch, some researchers use LLM performance on downstream tasks with documents as labels, but this approach requires manual answers for specific tasks, leading to high costs and limited generalization. In another line of work, prompting LLMs to select useful documents as RAG references eliminates the need for human annotation and is not task-specific. If we leverage LLMs’ utility judgments to annotate retrieval data, we may retain cross-task generalization without human annotation in large-scale corpora. Therefore, we investigate utility-focused annotation via LLMs for large-scale retriever training data across both in-domain and out-of-domain settings on the retrieval and RAG tasks. To reduce the impact of low-quality positives labeled by LLMs, we design a novel loss function, i.e., Disj-InfoNCE. Our experiments reveal that: (1) Retrievers trained on utility-focused annotations significantly outperform those trained on human annotations in the out-of-domain setting on both tasks, demonstrating superior generalization capabilities. (2) LLM annotation does not replace human annotation in the in-domain setting. However, incorporating just 20% human-annotated data enables retrievers trained with utility-focused annotations to match the performance of models trained entirely with human annotations, while adding 100% human annotations further significantly enhances performance on both tasks. We hope our wor

关键词： Human engineering

来源：评论

学校读者我要写书评

暂无评论

An RTDNN-Based Hybrid Precoding and Combining Joint Optimization Algorithm for MUPC-MIMO Systems

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and networking 2025年

作者： Liu, Fulai Liu, Yubiao Yang, Xianghuan Duan, Zhuoyao Shi, Baozhu Ji, Li Du, Ruiyan Northeastern University at Qinhuangdao Lab of Key Technology of Millimeter-wave Large-scale MIMO System Hebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao066004 China Hebei University College of Mathematics and Information Science Baoding071002 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Qinhuangdao Vocational and Technical College Qinhuangdao066100 China School of Computer Science and Engineering Northeastern University Shenyang110004 China

To achieve a satisfactory balance between energy efficiency (EE) and spectral efficiency (SE) for hybrid precoding and combining (HPC), this paper presents a two-stage joint optimization HPC algorithm based on residual deep neural network (DNN) for multi-user partially connected (MUPC) structure, namely RTDNN algorithm. In the proposed algorithm, a two-stage framework is designed to optimize analog and digital coders at the transmitter and receiver simultaneously, which can effectively preserve coupling relationship of coders between the transmitter and receiver. Specially, the RTDNN architecture is mainly divided into two stage networks, which includes analog stage and digital stage networks. The analog stage network is developed to obtain the optimal analog precoder and combiner simultaneously. On this basis, the digital stage network is constructed to solve the digital precoder and combiner concurrently. To further improve the prediction accuracy of RTDNN-based HPC, residual modules are adopted into the developed two stage networks. Moreover, the proposed RTDNN is trained with unsupervised learning. Simulation results show that the EE of the proposed algorithm is at least enhanced by 0.6 bits/Hz/J with satisfactory SE than other methods. © 2017 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Gradient sparsification for efficient wireless federated learning with differential privacy

引用

science China(Information sciences) 2024年第4期67卷 272-288页

作者： Kang WEI Jun LI Chuan MA Ming DING Feng SHU Haitao ZHAO Wen CHEN Hongbo ZHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education Data61 Commonwealth Scientific and Industrial Research Organisation School of Information and Communication Engineering Hainan University School of Communications and Information Engineering Nanjing University of Posts and Telecommunications School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University

Federated learning(FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy(DP)protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client's local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client's DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.

关键词： federated learning differential privacy gradient sparsification Lyapunov drift convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Learning to truncate ranked lists for information retrieval

arXiv

引用

arXiv 2021年

作者： Wu, Chen Zhang, Ruqing Guo, Jiafeng Fan, Yixing Lan, Yanyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Ranked list truncation is of critical importance in a variety of professional information retrieval applications such as patent search or legal search. The goal is to dynamically determine the number of returned documents according to some user-defined objectives, in order to reach a balance between the overall utility of the results and user efforts. Existing methods formulate this task as a sequential decision problem and take some pre-defined loss as a proxy objective, which suffers from the limitation of local decision and non-direct optimization. In this work, we propose a global decision based truncation model named AttnCut, which directly optimizes user-defined objectives for the ranked list truncation. Specifically, we take the successful transformer architecture to capture the global dependency within the ranked list for truncation decision, and employ the reward augmented maximum likelihood (RAML) for direct optimization. We consider two types of user-defined objectives which are of practical usage. One is the widely adopted metric such as F1 which acts as a balanced objective, and the other is the best F1 under some minimal recall constraint which represents a typical objective in professional search. Empirical results over the Robust04 and MQ2007 datasets demonstrate the effectiveness of our approach as compared with the state-of-the-art baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A linguistic study on relevance modeling in information retrieval

arXiv

引用

arXiv 2021年

作者： Fan, Yixing Guo, Jiafeng Ma, Xinyu Zhang, Ruqing Lan, Yanyan Cheng, Xueqi University of Chinese Academy of Sciences Beijing China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Relevance plays a central role in information retrieval (IR), which has received extensive studies starting from the 20th century. The definition and the modeling of relevance has always been critical challenges in both information science and computer science research areas. Along with the debate and exploration on relevance, IR has already become a core task in many real-world applications, such as Web search engines, question answering systems, conversational bots, and so on. While relevance acts as a unified concept in all these retrieval tasks, the inherent definitions are quite different due to the heterogeneity of these tasks. This raises a question to us: Do these different forms of relevance really lead to different modeling focuses? To answer this question, in this work, we conduct an empirical study on relevance modeling in three representative IR tasks, i.e., document retrieval, answer retrieval, and response retrieval. Specifically, we attempt to study the following two questions: 1) Does relevance modeling in these tasks really show differences in terms of natural language understanding (NLU)? We employ 16 linguistic tasks to probe a unified retrieval model over these three retrieval tasks to answer this question. 2) If there do exist differences, how can we leverage the findings to enhance the relevance modeling? We proposed three intervention methods to investigate how to leverage different modeling focuses of relevance to improve these IR tasks. We believe the way we study the problem as well as our findings would be beneficial to the IR community. © 2021, CC BY.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

FedMatch: Federated learning over heterogeneous question answering data

arXiv

引用

arXiv 2021年

作者： Chen, Jiangui Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Question Answering (QA), a popular and promising technique for intelligent information access, faces a dilemma about data as most other AI techniques. On one hand, modern QA methods rely on deep learning models which are typically data-hungry. Therefore, it is expected to collect and fuse all the available QA datasets together in a common site for developing a powerful QA model. On the other hand, real-world QA datasets are typically distributed in the form of isolated islands belonging to different parties. Due to the increasing awareness of privacy security, it is almost impossible to integrate the data scattered around, or the cost is prohibited. A possible solution to this dilemma is a new approach known as federated learning, which is a privacy-preserving machine learning technique over distributed datasets. In this work, we propose to adopt federated learning for QA with the special concern on the statistical heterogeneity of the QA data. Here the heterogeneity refers to the fact that annotated QA data are typically with non-identical and independent distribution (non-IID) and unbalanced sizes in practice. Traditional federated learning methods may sacrifice the accuracy of individual models under the heterogeneous situation. To tackle this problem, we propose a novel Federated Matching framework for QA, named FedMatch, with a backbone-patch architecture. The shared backbone is to distill the common knowledge of all the participants while the private patch is a compact and efficient module to retain the domain information for each participant. To facilitate the evaluation, we build a benchmark collection based on several QA datasets from different domains to simulate the heterogeneous situation in practice. Empirical studies demonstrate that our model can achieve significant improvements against the baselines over all the datasets. © 2021, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval

arXiv

引用

arXiv 2021年

作者： Ma, Xinyu Guo, Jiafeng Zhang, Ruqing Fan, Yixing Li, Yingyan Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Pre-training and fine-tuning have achieved remarkable success in many downstream natural language processing (NLP) tasks. Recently, pre-training methods tailored for information retrieval (IR) have also been explored, and the latest success is the PROP method which has reached new SOTA on a variety of ad-hoc retrieval benchmarks. The basic idea of PROP is to construct the representative words prediction (ROP) task for pre-training inspired by the query likelihood model. Despite its exciting performance, the effectiveness of PROP might be bounded by the classical unigram language model adopted in the ROP task construction process. To tackle this problem, we propose a bootstrapped pre-training method (namely B-PROP) based on BERT for ad-hoc retrieval. The key idea is to use the powerful contextual language model BERT to replace the classical unigram language model for the ROP task construction, and re-train BERT itself towards the tailored objective for IR. Specifically, we introduce a novel contrastive method, inspired by the divergence-from-randomness idea, to leverage BERT's self-attention mechanism to sample representative words from the document. By further fine-tuning on downstream ad-hoc retrieval tasks, our method achieves significant improvements over PROP and other baselines, and further pushes forward the SOTA on a variety of ad-hoc retrieval tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering

arXiv

引用

arXiv 2021年

作者： Wu, Yunfan Cao, Qi Shen, Huawei Tao, Shuchang Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China Data Intelligence System Research Center Institute of Computing Technology CAS China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China

Collaborative filtering is one of the most common scenarios and popular research topics in recommender systems. Among existing methods, latent factor models, i.e., learning a specific embedding for each user/item by reconstructing the observed interaction matrix, have shown excellent performances. However, such user-specific and item-specific embeddings are intrinsically transductive, making it difficult to deal with new users and new items unseen during training. Besides, the number of model parameters heavily depends on the number of all users and items, restricting its scalability to real-world applications. To solve the above challenges, in this paper, we propose a novel model-agnostic and scalable Inductive Embedding Module for collaborative filtering, namely INMO. INMO generates the inductive embeddings for users (items) by characterizing their interactions with some template items (template users), instead of employing an embedding lookup table. Under the theoretical analysis, we further propose an effective indicator for the selection of template users/items. Our proposed INMO can be attached to existing latent factor models as a pre-module, inheriting the expressiveness of backbone models, while bringing the inductive ability and reducing model parameters. We validate the generality of INMO by attaching it to both Matrix Factorization (MF) and LightGCN, which are two representative latent factor models for collaborative filtering. Extensive experiments on three public benchmarks demonstrate the effectiveness and efficiency of INMO in both transductive and inductive recommendation scenarios. © 2021, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Dear-DIA^(XMBD): Deep Autoencoder Enables Deconvolution of data-Independent Acquisition Proteomics

引用

Research 2024年第1期6卷 707-720页

作者： Qingzu He Chuan-Qi Zhong Xiang Li Huan Guo Yiming Li Mingxuan Gao Rongshan Yu Xianming Liu Fangfei Zhang Donghui Guo Fangfu Ye Tiannan Guo Jianwei Shuai Jiahuai Han Department of Physics and Fujian Provincial Key Laboratory for Soft Functional Materials ResearchXiamen UniversityXiamen 361005China Oujiang Laboratory(Zhejiang Lab for Regenerative Medicine Vision and Brain Health)and Wenzhou InstituteUniversity of Chinese Academy of SciencesWenzhouZhejiang 325001China School of Life Sciences Xiamen UniversityXiamen 361102China State Key Laboratory of Cellular Stress Biology Innovation Center for Cell Signaling NetworkXiamen 361102China Department of Computer Science Xiamen UniversityXiamen 361005China National Institute for Data Science in Health and Medicine School of MedicineXiamen UniversityXiamen 361102China Bruker(Beijing)Scientific Technology Co.Ltd. BeijingChina Westlake Laboratory of Life Sciences and Biomedicine Key Laboratory of Structural Biology of Zhejiang ProvinceSchool of Life SciencesWestlake University18 Shilongshan RoadHangzhou 310024China Institute of Basic Medical Sciences Westlake Institute for Advanced Study18 Shilongshan RoadHangzhou 310024China Westlake Omics Ltd. Yunmeng Road 1HangzhouChina Department of Electronic Engineering Xiamen UniversityXiamen 361005China

data-independent acquisition(DIA)technology for protein identification from mass spectrometry and related algorithms is developing *** spectrum-centric analysis of DIA data without the use of spectra library from data-dependent acquisition data represents a promising *** this paper,we proposed an untargeted analysis method,Dear-DIA^(XMBD),for direct analysis of DIA ***-DIA^(XMBD) first integrates the deep variational autoencoder and triplet loss to learn the representations of the extracted fragment ion chromatograms,then uses the k-means clustering algorithm to aggregate fragments with similar representations into the same classes,and finally establishes the inverted index tables to determine the precursors of fragment clusters between precursors and peptides and between fragments and *** show that Dear-DIA^(XMBD) performs superiorly with the highly complicated DIA data of different species obtained by different instrument platforms.

关键词： Deep Auto Independent

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

arXiv

引用

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. 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

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：