检索结果-内蒙古大学图书馆

Long and Recent Preference Learning with Recent-k Items Distribution for Recommender System

IEEE Transactions on Multimedia 2025年

作者： Gao, Yongbiao Niu, Sijie Lv, Guohua Ling, Miaogen Geng, Xin Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China Southeast University Ministry of Education Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing School of Information Science and Engineering China Nanjing University of Information Science and Technology School of Computer Science China Southeast University School of Computer Science and Engineering China

Reinforcement learning (RL) aims to formulate the recommendation task as a Markov decision process (MDP) and trains an agent to automatically learn the optimal recommendation policy from interaction trajectories through trial-and-error and reward mechanisms. However, most existing RL-based approaches overlook the correlation between items and the dynamics of user interests implied in temporally close interactions. Therefore, in this paper, we propose a reinforcement learning method that incorporates a "recent-k items"distribution to capture users' local preferences. Specifically, we model the output layer as two distinct branches. The "recent-k items"branch, formulated with a Kullback-Leibler divergence loss, learns the recent interests of users, whereas the other branch utilizes a one-step temporal difference error to capture long-term preferences. The proposed structure is integrated into deep Q-learning and actor-critics, resulting in two enhanced methods named R k Q and R k AC, respectively. Furthermore, a novel soft inter-reward is carefully designed to enhance the proposed method, and we theoretically prove the convergence of the proposed algorithm. We perform extensive experiments on two large real-world datasets and conduct further analysis of the influences of different action sequences, time intervals, and enhancement capabilities for state-of-the-art models. The experimental results demonstrate the efficacy of our proposed methods. © 1999-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Positive-Guided Knowledge Distillation for Document-Level Relation Extraction with Noisy Labeled Data 12th

Positive-Guided Knowledge Distillation for Document-Level R...

引用

12th National CCF Conference on Natural Language Processing and Chinese computing, NLPCC 2023

作者： Zeng, Daojian Zhu, Jianling Jiang, Lincheng Dai, Jianhua Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Institute of AI and Targeted International Communication Hunan Normal University Changsha China College of Advanced Interdisciplinary Studies National University of Defense Technology Changsha China

ISBN: (纸本)9783031446924

Since one entity may have multiple mentions and relations between entities may stretch across multiple sentences in a document, the annotation of document-level relation extraction datasets becomes a challenging task. Many studies have identified that these datasets contain a large number of noisy labels, hindering performance improvement for the document-level relation extraction task. The previous and most straightforward method is denoising noisy labeled data from a data annotation perspective. However, this time-consuming approach is not suitable for large-scale datasets. In this paper, we propose a novel Positive-Guided Knowledge Distillation (PGKD) model to address the noisy labeled data problem for document-level relation extraction. We design a new teacher-student architecture. The teacher model trained with only positive samples can partially supervise the student model. The positive-guided knowledge distillation algorithm transfers the clean positive-class patterns from the teacher model to the student model. In this way, the student model trained with all samples can efficiently prevent the interference of false negative samples. Extensive experiments on Mix-DocRED demonstrate that PGKD achieves state-of-the-art effectiveness for document-level relation extraction with noisy labeled data. Moreover, PGKD also surpasses other baselines even on the well-annotated Re-DocRED. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Exploring Query Efficient Data Generation Towards Data-Free Model Stealing in Hard Label Setting 39

Exploring Query Efficient Data Generation Towards Data-Free ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pei, Gaozheng Lyu, Shaojie Ma, Ke Yang, Pinci Xu, Qianqian Sun, Yingfei School of Electronic Electrical and Communication Engineering UCAS Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China Tencent Corporate China

ISBN: (纸本)157735897X

Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model’s structure, parameters, or training data. The adversary can only access the target model’s predictions for generated samples. Once the substitute model closely approximates the behavior of the target model, attackers can exploit its white-box characteristics for subsequent malicious activities, such as adversarial attacks. Existing methods within cooperative game frameworks often produce samples with high confidence for the prediction of the substitute model, which makes it difficult for the substitute model to replicate the behavior of the target model. This paper presents a new data-free model stealing approach called Query Efficient Data Generation (QEDG). We introduce two distinct loss functions to ensure the generation of sufficient samples that closely and uniformly align with the target model’s decision boundary across multiple classes. Building on the limitation of current methods, which typically yield only one piece of supervised information per query, we propose the query-free sample augmentation that enables the acquisition of additional supervised information without increasing the number of queries. Motivated by theoretical analysis, we adopt the consistency rate metric, which more accurately evaluates the similarity between the substitute and target models. We conducted extensive experiments to verify the effectiveness of our proposed method, which achieved better performance with fewer queries compared to the state-of-the-art methods on the real MLaaS scenario and five datasets. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation 39

Large Language Models Are Read/Write Policy-Makers for Simul...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Shoutao Zhang, Shaolei Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)157735897X

Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policymakers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propose a novel LLM-driven Simultaneous Generation (LSG) framework, which allows the off-the-shelf LLM to decide the generation timing and produce output concurrently. Specifically, LSG selects the generation policy that minimizes latency as the baseline policy. Referring to the baseline policy, LSG enables the LLM to devise an improved generation policy that better balances latency and generation quality, and writes generation results accordingly. Experiments on simultaneous translation and streaming automatic speech recognition tasks show that our method can achieve state-of-the-art performance utilizing the open-source LLMs and demonstrate practicality in real-world scenarios. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

arXiv

引用

arXiv 2024年

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

SPTNET: Span-based Prompt Tuning for Video Grounding

SPTNET: Span-based Prompt Tuning for Video Grounding

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiren Zhang Yuanwu Xu Mohan Chen Yuejie Zhang Rui Feng Shang Gao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Information Technology Deakin University

When a Pre-trained Language Model (PLM) is adopted in video grounding task, it usually acts as a text encoder without having its knowledge fully utilized. Also, there exists an inconsistency problem between the pre-training and downstream objectives. To solve the issues, we propose a new paradigm, named Span-based Prompt Tuning (SPTNet). It can convert the video grounding task into a cloze form. Specifically, a query is first changed into a form with mask token by a template, then the video and the query embeddings are integrated through a cross-modal transformer. The start and end points of the query matching time span are predicted with the embedding of the mask token. Experimental results on two public benchmarks ActivityNet Captions and Charades-STA show that our SPTNet achieves surpassing performance compared with state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Finite-Difference Time-Domain Method for Solving Electromagnetic Scattering in Layered Anisotropies

Efficient Finite-Difference Time-Domain Method for Solving E...

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Yilin Kang Yuxian Zhang Xiaoli Feng Lixia Yang Zhixiang Huang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education and with the Information Materials and Intelligent Sensing Laboratory of Anhui Province Industry-Education-Research Institute of Advanced Materials and Technology for Integrated Circuits and with School of Electronic and Information Engineering Anhui University Hefei China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

In this article, we propose an efficient numerical method for layered models based on the conventional finite difference time-domain (FDTD) method. The three-dimensional (3-D) layered model is compressed into one-dimensional (1-D) calculation, which improves the problem of large space memory and long running time for 3-D modeling while ensuring the accuracy and feasibility of the algorithm. On the one hand, by employing the transformation relationship between the transverse wave vector and the field in space, the expanded Maxwell's rotation equations are simplified, so that the equation system only retains the spatial transformation in the propagation direction. This processing allows for the calculation of the propagation characteristics of layered media without requiring more computational resources. On the other hand, to ensure the universality of the algorithm, a fully tensor anisotropic medium is selected for detecting the propagation data. At the same time, we design the layered structure and conduct the consistent 3-D modeling in the simulation software COMSOL. The results showed that our proposed efficient numerical algorithm greatly reduced the loss of computing resources while ensuring accuracy.

关键词： Solid modeling Three-dimensional displays Accuracy Tensors Software algorithms Vectors Mathematical models Numerical models Time-domain analysis Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

Conditional Video-Text Reconstruction Network with Cauchy Mask for Weakly Supervised Temporal Sentence Grounding

Conditional Video-Text Reconstruction Network with Cauchy Ma...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jueqi Wei Yuanwu Xu Mohan Chen Yuejie Zhang Rui Feng Shang Gao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Information Technology Deakin University

Temporal sentence grounding aims to detect the target segment most related to a given query in an untrimmed video. To alleviate the expensive annotation cost for temporal labels, researchers paid more attention to weakly supervised setting. Prior studies neglected the utilization of video representation reconstruction, which led to an unbalanced alignment learning. Moreover, they used different strategies to generate proposals which ignored the temporal structure in a query. In this paper, we propose a novel Conditional Video-Text Reconstruction Network (CVTRN). It supports conditional reconstruction of video and text representation. Specifically, video and text features are fused to compute semantic alignment, which is the condition of reconstruction. A new mask strategy for mask conditioned sentence reconstruction is also devised. This strategy focuses more on boundary regions than the widely used Gaussian mask in previous methods. Experimental results on two public benchmark datasets show that our CVTRN outperforms the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relation-Based Multi-Teacher Knowledge Distillation

Relation-Based Multi-Teacher Knowledge Distillation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yutian Wang Yi Xu School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu China Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Traditional knowledge distillation adopts one teacher model to instruct the training of a lightweight student model. To improve the performance of knowledge distillation, multi-teacher knowledge distillation utilizing multi-party knowledge to guide model learning was proposed. However, existing methods mainly use the summation-result of teacher models of a single sample to integrate multi-party knowledge directly, ignoring the relation knowledge among samples. In this paper, we propose a novel multi-teacher knowledge distillation method, which utilizes the data relation knowledge to allocate weights for teachers adaptively. To obtain the data relation knowledge, we design output-based strategy and feature-based strategy, which would help to allocate more weight for the teacher who has better learned the data relation knowledge. Extensive experiments have demonstrated the performance and efficiency of our proposed multi-teacher knowledge distillation method.

关键词： Training Adaptation models Neural networks

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional Data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

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：