检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shao, Chenze Ma, Zhengrui Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning. Copyright © 2023, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

SSE-SAM: Balancing Head and Tail Classes Gradually Through Stage-Wise SAM 39

SSE-SAM: Balancing Head and Tail Classes Gradually Through S...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lyu, Xingyu Xu, Qianqian Yang, Zhiyong Lyu, Shaojie Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Tencent Corporate China BDKM University of Chinese Academy of Sciences China

ISBN: (纸本)157735897X

Real-world datasets often exhibit a long-tailed distribution, where vast majority of classes known as tail classes have only few samples. Traditional methods tend to overfit on these tail classes. Recently, a new approach called Imbalanced SAM (ImbSAM) is proposed to leverage the generalization benefits of Sharpness-Aware Minimization (SAM) for long-tailed distributions. The main strategy is to merely enhance the smoothness of the loss function for tail classes. However, we argue that improving generalization in long-tail scenarios requires a careful balance between head and tail classes. We show that neither SAM nor ImbSAM alone can fully achieve this balance. For SAM, we prove that although it enhances the model's generalization ability by escaping saddle point in the overall loss landscape, it does not effectively address this for tail-class losses. Conversely, while ImbSAM is more effective at avoiding saddle points in tail classes, the head classes are trained insufficiently, resulting in significant performance drops. Based on these insights, we propose Stage-wise Saddle Escaping SAM (SSE-SAM), which uses complementary strengths of ImbSAM and SAM in a phased approach. Initially, SSE-SAM follows the majority sample to avoid saddle points of the head-class loss. During the later phase, it focuses on tail-classes to help them escape saddle points. Our experiments confirm that SSE-SAM has better ability in escaping saddles both on head and tail classes, and shows performance improvements. Copyright © 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

Nonnegative Matrix Factorization Based on Topology-and-Attribute-Matching Degree for Community Detection 18th

Nonnegative Matrix Factorization Based on Topology-and-Attr...

引用

18th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2023

作者： Zeng, Ruolan Liu, Zhanghui Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819996360

Community detection is widely used in network analysis, which seeks to divide network nodes into distinct communities based on the topology structure and attribute information of the network. Due to its interpretability, nonnegative matrix factorization becomes an essential method for community detection. However, it decomposes the adjacency matrix and attribute matrix separately, which do not tightly incorporate topology and attributes. And in the problem of division inconsistency based on topology and attributes caused by the mismatch between the topology similarity and attribute similarity of paired nodes, it ignores the difference in the matching degree of each attribute and each node. In this paper, we propose a nonnegative matrix factorization algorithm for community detection (MTACD) based on the matching degree between topology and attribute. First, we employ an attribute embedding mechanism to enhance the node-attribute relationship. Second, we design an attribute matching degree and a node topology-and-attribute matching degree in order to resolve the mismatch between topology and attribute similarity. Experiments on both real-world and synthetic networks demonstrate the effectiveness of our algorithm. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Fixed-Parameter Tractability for Book Drawing with Bounded Number of Crossings per Edge 15th

Fixed-Parameter Tractability for Book Drawing with Bounded...

引用

15th International Conference on Algorithmic Aspects in information and Management, AAIM 2021

作者： Liu, Yunlong Li, Yixuan Huang, Jingui College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China Hunan Xiangjiang Artificial Intelligence Academy Changsha China

ISBN: (纸本)9783030931759

The problem book drawing with a bounded number of crossings per edge asks, given a graph G= (V, E) and two integers k, b, whether there is a k-page book drawing of G such that the maximum number of crossings per edge is at most b. In this paper, we study this problem from a parameterized complexity viewpoint. Specifically, we investigate the problem parameterized by both the maximum number b of crossings per edge and the vertex cover number τ of G, and show that this parameterized problem admits a kernel of size (3 b+ 1 ) · 2O(τ) and admits a fixed-parameter tractable algorithm running in time O((3b+1)·2(3b+2)·2O(τ)+τ·|V| ). Together with our previous result for fixed-order book drawing with a bounded number of crossings per edge (COCOA 2020), our result provides a more complete answer to a question posed by Bhore et al. (J. Graph Alg. Appl. 2020). © 2021, Springer Nature Switzerland AG.

关键词： Parameterization

来源：评论

学校读者我要写书评

暂无评论

Restricted Arc-Connectivity of Unidirectional Star Graphs

SSRN

引用

SSRN 2022年

作者： Zhao, Xiaojun Deng, Qingying Wang, Zhiyi Key Laboratory of Intelligent Computing & Information Processing of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

The restricted arc-connectivity is an effective assessment of the reliability of directed networks, which is an extended notion of arc-connectivity. An arc set S of D is a restricted arc-cut of D if D−S has a strong connected component D′ such that |V (D′)| ≥ 2 and D−V (D′) contains an arc. D is called λ′-connected if there exists a restricted arc-cut in D. The restricted arc-connectivity λ′(D) of a λ′-connected digraph D is the minimum cardinality over all restricted arc-cuts. We can get a unidirectional star graph by orienting the star graph with Day-Tripathi orientation. In this paper, we first show that the restricted arc-connectivity of the n-dimensional unidirectional star graph is n−2 when n is odd and n−3 when n is even for n ≥ 4. As a consequence, we prove that unidirectional star graph is super-λ. © 2022, The Authors. All rights reserved.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Dual-State Personalized Knowledge Tracing with Emotional Incorporation

arXiv

引用

arXiv 2024年

作者： Wang, Shanshan Yuan, Fangzheng Wang, Keyang Yang, Xun Zhang, Xingyi Wang, Meng Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei230601 China Zhejiang Dahua Technology Co. Ltd China Department of Electronic Engineering and Information Science School of information Science and Technology University of Science and Technology of China Hefei230026 China Key Laboratory of intelligent computing and Signal Processing Ministry of Education school of Computer Science and Technology Anhui University Hefei230601 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

Knowledge tracing has been widely used in online learning systems to guide the students' future learning. However, most existing KT models primarily focus on extracting abundant information from the question sets and explore the relationships between them, but ignore the personalized student behavioral information in the learning process. This will limit the model's ability to accurately capture the personalized knowledge states of students and reasonably predict their performances. To alleviate this limitation, we explicitly models the personalized learning process by incorporating the emotions, a representative personalized behavior in the learning process, into KT framework. Specifically, we present a novel Dual-State Personalized Knowledge Tracing with Emotional Incorporation model to achieve this goal: Firstly, we incorporate emotional information into the modeling process of knowledge state, resulting in the Knowledge State Boosting Module. Secondly, we design an Emotional State Tracing Module to monitor students' personalized emotional states, and propose an emotion prediction method based on personalized emotional states. Finally, we apply the predicted emotions to enhance students' response prediction. Furthermore, to extend the generalization capability of our model across different datasets, we design a transferred version of DEKT, named Transfer Learningbased Self-loop model (T-DEKT). Extensive experiments show our method achieves the state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Multi-Granularity Feature Distillation Learning Network for Fine-Grained Visual Classification

Multi-Granularity Feature Distillation Learning Network for ...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Yuhang Cai Xiao Ke Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou Fujian China

ISBN: (纸本)9781665464697

Fine-grained visual classification (FGVC) aims to identify objects belonging to multiple sub-categories of the same super-category (such as species of birds, models of cars and aircraft). The key to solving fine-grained classification problems is to learn discriminative visual feature representation with only subtle differences. Although previous work based on refined feature learning has made great progress, however, high-level semantic features often lack key information for fine-grained visual object nuances. How to efficiently integrate semantic information of different granularities from classification networks is a Critical. In this paper, we propose Multi-Granularity Feature Distillation Learning Network (MGFDL-Net). Our solution integrates multi-granularity hierarchical information through a multi-granularity fusion learning strategy to enhance feature representation. In view of the inherent challenges of large intraclass differences in FGVC, a cross-layer self-distillation regularization is proposed to strengthen the connection between high-level semantics and low-level semantics for robust multi-granularity feature learning. Comprehensive experiments show that our method achieves state-of-the-art performance on three challenging fine-grained visual classification FGVC datasets (CUB-200-2011, Stanford Cars and FGVC-Aircraft).

关键词： Representation learning Visualization Cross layer design Computer vision Image processing Semantics Birds

来源：评论

学校读者我要写书评

暂无评论

Modality-specific Adaptive Scaling Method for Cross-modal Retrieval

Modality-specific Adaptive Scaling Method for Cross-modal Re...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Baitao Chen Xiao Ke Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou Fujian China

ISBN: (纸本)9781665464697

There are huge differences in data distribution and feature representation of different modalities. How to flexibly and accurately retrieve data from different modalities is a challenging problem. The mainstream common subspace method only focus on the heterogeneity gap between modalities, and use a unified method to jointly learn the common representation of different modalities, which can easily lead to the difficulty of multi-modal unified fitting. In this work, we innovatively propose the concept of multi-modal information density discrepancy, and propose a modality-specific adaptive scaling method incorporating prior knowledge, which can adaptively learn the most suitable network for different modalities. Comprehensive experimental results on three widely used cross-modal retrieval datasets show the proposed MASM achieves the state-of-the-art results and significantly outperforms other existing methods.

关键词： Knowledge engineering Computer vision Adaptive systems Image processing Fitting Machine learning

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework

arXiv

引用

arXiv 2023年

作者： Wang, Shiping Wu, Zhihao Chen, Yuhong Chen, Yong College of Computer and Data Science Fuzhou University China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University China School of Computer Science Beijing University of Posts and Telecommunications China

Graph convolutional networks (GCNs) have been attracting widespread attentions due to their encouraging performance and powerful generalizations. However, few work provide a general view to interpret various GCNs and guide GCNs’ designs. In this paper, by revisiting the original GCN, we induce an interpretable regularizer-centerd optimization framework, in which by building appropriate regularizers we can interpret most GCNs, such as APPNP, JKNet, DAGNN, and GNN-LF/HF. Further, under the proposed framework, we devise a dual-regularizer graph convolutional network (dubbed tsGCN) to capture topological and semantic structures from graph data. Since the derived learning rule for tsGCN contains an inverse of a large matrix and thus is time-consuming, we leverage the Woodbury matrix identity and low-rank approximation tricks to successfully decrease the high computational complexity of computing infinite-order graph convolutions. Extensive experiments on eight public datasets demonstrate that tsGCN achieves superior performance against quite a few state-of-the-art competitors w.r.t. classification *** Codes 68T07 Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

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：