检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Xiaodong Hu, Yuxuan Zhang, Xiaokang Wang, Yanling Li, Cuiping Chen, Hong Zhang, Jing School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Zhongguancun Laboratory China

Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). To recover model performance after pruning, post-training is commonly employed to mitigate the resulting performance degradation. While post-training benefits from larger datasets, once the dataset size is already substantial, increasing the training data provides only limited performance gains. To balance post-training cost and model performance, it is necessary to explore the optimal amount of post-training data. Through extensive experiments on the Llama-3 and Qwen-2.5 series models, pruned using various common pruning methods, we uncover the scaling Law for Post-training after model Pruning, referred to as the P2 Law. This law identifies four key factors for predicting the pruned model’s post-training loss: the model size before pruning, the number of post-training tokens, the pruning rate, and the model’s loss before pruning. Moreover, P2 Law can generalize to larger dataset sizes, larger model sizes, and higher pruning rates, offering valuable insights for the post-training of pruned LLMs. © 2024, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Dynamic Scaling of Unit Tests for Code Reward Modeling

arXiv

引用

arXiv 2025年

作者： Ma, Zeyao Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie School of Information Renmin University of China China Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China

Current large language models (LLMs) often struggle to produce accurate solutions on the first attempt for code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus). © 2025, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Partial Label Feature Selection: An Adaptive Approach

引用

IEEE Transactions on knowledge and data engineering 2024年第8期36卷 4178-4191页

作者： Zan Zhang Jialu Yao Lin Liu Jiuyong Li Lei Li Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei Anhui China School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei Anhui China UniSA STEM University of South Australia Adelaide SA Australia Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology Hefei Anhui China

As an emerging weakly supervised learning framework, partial label learning aims to induce a multi-class classifier from ambiguous supervision information where each training example is associated with a set of candidate labels, among which only one is the true label. Traditional feature selection methods, either for single label and multiple label problems, are not applicable to partial label learning as the ambiguous information contained in the label space obfuscates the importance of features and misleads the selection process. This makes the selection of a proper feature subset from partial label examples particularly challenging, and therefore has rarely been investigated. In this paper, we propose a novel feature selection algorithm for partial label learning, named PLFS, which considers not only the relationships between features and labels, but also exploits the relationships between instances to select the most informative and important features to enhance the performance of partial label learning. PLFS constructs an adaptive weighted graph to exploit the similarity information among instances, differentiate the label space and weight the feature space, which leads to the selection of a proper feature subset. Extensive experiments over a broad range of benchmark data sets clearly validate the effectiveness of our proposed feature selection approach.

关键词： Feature extraction Supervised learning Training knowledge engineering Labeling Classification algorithms Big data

来源：评论

学校读者我要写书评

暂无评论

Automatic Fusion for Multimodal Entity Alignment: A New Perspective from Automatic Architecture Search

Automatic Fusion for Multimodal Entity Alignment: A New Pers...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chenyang Bu Yunpeng Hong Shiji Zang Guojie Chang Xindong Wu Key Laboratory of Knowledge Engineering With Big Data (the Ministry of Education of China) School of Computer Science and Engineering HeFei University of Technology

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Integrating multimodal data from diverse sources is crucial for enhancing various applications. Multimodal entity alignment (MMEA), which discovers equivalent entities across different sources and modalities, aims to eliminate data silos for comprehensive integration. A key challenge in MMEA is effectively fusing vector representations from different modalities of the same entity for optimal entity matching. Existing fusion methods involve individual fusion operators (e.g., concatenation and summation) or the manual design of complex network structures, incurring significant human resource costs. In this paper, for the first time, we introduce the research question of automatic fusion for MMEA and propose an efficient approach from the perspective of automated architecture search. Experimental comparisons with state-of-the-art methods on real-world datasets demonstrate the effectiveness of the proposed approach.

关键词： Costs Search methods Complex networks Vectors

来源：评论

学校读者我要写书评

暂无评论

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective 39

Revisiting Graph Contrastive Learning on Anomaly Detection: ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Yiming Peng, Zhen Shi, Bin Hua, Xu Dong, Bo Wang, Song Chen, Chen School of Computer Science and Technology Xi'an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China School of Distance Education Xi'an Jiaotong University China University of Virginia CharlottesvilleVA United States

ISBN: (纸本)157735897X

The superiority of graph contrastive learning (GCL) has prompted its application to anomaly detection tasks for more powerful risk warning systems. Unfortunately, existing GCL-based models tend to excessively prioritize overall detection performance while neglecting robustness to structural imbalance, which can be problematic for many real-world networks following power-law degree distributions. Particularly, GCL-based methods may fail to capture tail anomalies (abnormal nodes with low degrees). This raises concerns about the security and robustness of current anomaly detection algorithms and therefore hinders their applicability in a variety of realistic high-risk scenarios. To the best of our knowledge, research on the robustness of graph anomaly detection to structural imbalance has received little scrutiny. To address the above issues, this paper presents a novel GCL-based framework named AD-GCL. It devises the neighbor pruning strategy to filter noisy edges for head nodes and facilitate the detection of genuine tail nodes by aligning from head nodes to forged tail nodes. Moreover, AD-GCL actively explores potential neighbors to enlarge the receptive field of tail nodes through anomaly-guided neighbor completion. We further introduce intra- and inter-view consistency loss of the original and augmentation graph for enhanced representation. The performance evaluation of the whole, head, and tail nodes on multiple datasets validates the comprehensive superiority of the proposed AD-GCL in detecting both head anomalies and tail anomalies. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

A Part-of-Speech Tagging Model Employing Word Clustering and Syntactic Parsing

引用

Chinese Journal of Electronics 2025年第1期23卷 109-114页

作者： Lichi Yuan School of Information Technology Jiangxi University of Finance and Economics Nanchang China Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang China

Part-Of-Speech tagging is a basic task in the field of natural language processing. This paper builds a POS tagger based on improved Hidden Markov model, by employing word clustering and syntactic parsing model. Firstly, In order to overcome the defects of the classical HMM, Markov family model (MFM), a new statistical model was introduced. Secondly, to solve the problem of data sparseness, we propose a bottom-to-up hierarchical word clustering algorithm. Then we combine syntactic parsing with part-of-speech tagging. The Part-of-Speech tagging experiments show that the improved Part-Of-Speech tagging model has higher performance than Hidden Markov models (HMMs) under the same testing conditions, the precision is enhanced from 94.642% to 97.235%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Generalization on Graphs via Progressive Inference 39

Out-of-Distribution Generalization on Graphs via Progressive...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Yiming Shi, Bin Peng, Zhen Liu, Huixiang Dong, Bo Chen, Chen School of Computer Science and Technology Xi'an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University China School of Distance Education Xi'an Jiaotong University China University of Virginia CharlottesvilleVA United States

ISBN: (纸本)157735897X

The development and evaluation of graph neural networks (GNNs) generally follow the independent and identically distributed (i.i.d.) assumption. Yet this assumption is often untenable in practice due to the uncontrollable data generation mechanism. In particular, when the data distribution shows a significant shift, most GNNs would fail to produce reliable predictions and may even make decisions randomly. One of the most promising solutions to improve the model generalization is to pick out causal invariant parts in the input graph. Nonetheless, we observe a significant distribution gap between the causal parts learned by existing methods and the ground-truth, leading to undesirable performance. In response to the above issues, this paper presents GPro, a model that learns graph causal invariance with progressive inference. Specifically, the complicated graph causal invariant learning is decomposed into multiple intermediate inference steps from easy to hard, and the perception of GPro is continuously strengthened through a progressive inference process to extract causal features that are stable to distribution shifts. We also enlarge the training distribution by creating counterfactual samples to enhance the capability of the GPro in capturing the causal invariant parts. Extensive experiments demonstrate that our proposed GPro outperforms the state-of-the-art methods by 4.91% on average. For datasets with more severe distribution shifts, the performance improvement can be up to 6.86%. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Measuring China's Real Estate Financial Innovation from the Perspective of Government,Enterprises and the Public:Index Compilation and Its Spatial-Temporal Characteristics Analysis

引用

Journal of Systems Science and Information 2023年第1期11卷 1-34页

作者： Jichang DONG Lijun YIN Xiaoting LIU Xiuting LI School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China China Construction Second Engineering Bureau Co.Ltd Beijing 100070China

In recent years,China has witnessed the rapid development in housing finance,and there have emerged constantly real estate finance innovations;however,there exists no relevant index for measuring the innovations of China's real estate *** on the perspectives of the governments,enterprises and the public,this paper constructs the"innovation index of real estate finance"on a quarterly basis from 2009 to 2019,with the method of empowerment which combines the subjective method(analytic hierarchy process)and the objective one(range coefficient method).It clearly and concretely depicts the innovations in housing finance and the related temporal-spatial characteristics in China since the outbreak of the financial crisis in *** index covers 30 provinces,autonomous regions and municipalities directly under the central government,and analyzes its temporal and spatial *** findings show that there exist a strong spatial autocorrelation and a big regional difference in innovations.

关键词： governments enterprises public real estate finance innovation

来源：评论

学校读者我要写书评

暂无评论

PSDiff: Diffusion Model for Person Search With Iterative and Collaborative Refinement

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5153-5165页

作者： Jia, Chengyou Luo, Minnan Dang, Zhuohang Dai, Guang Chang, Xiaojun Wang, Jingdong Xi’an Jiaotong University School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China SGIT AI Laboratory Xi’an710048 China State Grid Corporation of China State Grid Shaanxi Electric Power Company Ltd. Xi’an710048 China University of Science and Technology of China School of Information Science and Technology Hefei230031 China Abu Dhabi United Arab Emirates Baidu Inc. Beijing100085 China

Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes the two sub-tasks of pedestrian detection and Re-Identification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

SLMP: A Scientific Literature Management Platform Based on Large Language Models 15

SLMP: A Scientific Literature Management Platform Based on L...

引用

15th IEEE International Conference on knowledge Graph, ICKG 2024

作者： Guo, Menghao Jiang, Jinling Wu, Fan Sun, Shanxin Zhang, Chen Li, Wenhui Sun, Zeyi Chen, Guangyong Wu, Xindong Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Hefei University of Technology Key Laboratory of Knowledge Engineering With Big Data Hefei China

ISBN: (纸本)9798331508821

This paper presents a Scientific Literature Management Platform (SLMP, demo link1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge. © 2024 IEEE.

关键词： Question answering

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：