检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Yingji Du, Mengnan Song, Rui Wang, Xin Wang, Ying College of Computer Science and Technology Jilin University Changchun130012 China Department of Data Science New Jersey Institute of Technology Newark United States School of Artificial Intelligence Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Changchun130012 China

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide existing fairness research into oriented to medium-sized LLMs under pre-training and fine-tuning paradigms and oriented to large-sized LLMs under prompting paradigms. First, for medium-sized LLMs, we introduce evaluation metrics and debiasing methods from the perspectives of intrinsic bias and extrinsic bias, respectively. Then, for large-sized LLMs, we introduce recent fairness research, including fairness evaluation, reasons for bias, and debiasing methods. Finally, we discuss and provide insight on the challenges and future directions for the development of fairness in LLMs. Copyright © 2023, The Authors. All rights reserved.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Object Attribute Matters in Visual Question Answering

arXiv

引用

arXiv 2023年

作者： Li, Peize Si, Qingyi Fu, Peng Lin, Zheng Wang, Yan School of Artificial Intelligence Jilin University Changchun China 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 Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun China

Visual question answering is a multimodal task that requires the joint comprehension of visual and textual information. However, integrating visual and textual semantics solely through attention layers is insufficient to comprehensively understand and align information from both modalities. Intuitively, object attributes can naturally serve as a bridge to unify them, which has been overlooked in previous research. In this paper, we propose a novel VQA approach from the perspective of utilizing object attribute, aiming to achieve better object-level visual-language alignment and multimodal scene understanding. Specifically, we design an attribute fusion module and a contrastive knowledge distillation module. The attribute fusion module constructs a multimodal graph neural network to fuse attributes and visual features through message passing. The enhanced object-level visual features contribute to solving fine-grained problem like counting-question. The better object-level visual-language alignment aids in understanding multimodal scenes, thereby improving the model’s robustness. Furthermore, to augment scene understanding and the out-of-distribution performance, the contrastive knowledge distillation module introduces a series of implicit knowledge. We distill knowledge into attributes through contrastive loss, which further strengthens the representation learning of attribute features and facilitates visual-linguistic alignment. Intensive experiments on six datasets, COCO-QA, VQAv2, VQA-CPv2, VQA-CPv1, VQAvs and TDIUC, show the superiority of the proposed method. © 2023, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering

arXiv

引用

arXiv 2024年

作者： Li, Peize Si, Qingyi Fu, Peng Lin, Zheng Wang, Yan School of Artificial Intelligence Jilin University Changchun China Institute of Information Engineering Chinese Academy of Sciences Beijing China Huawei Technologies Co. Ltd. Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University Changchun China

Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "retrieve-then-answer" pipelines often suffer from cascading errors because the training objective of QA fails to optimize the retrieval stage. To address this issue, we propose a novel method to effectively introduce and reference retrieved information into the QA. Given the image set to be retrieved, we employ a multimodal large language model (visual perspective) and a large language model (textual perspective) to obtain multimodal hypothetical summary in question-form and description-form. By combining visual and textual perspectives, MHyS captures image content more specifically and replaces real images in retrieval, which eliminates the modality gap by transforming into text-to-text retrieval and helps improve retrieval. To more advantageously introduce retrieval with QA, we employ contrastive learning to align queries (questions) with MHyS. Moreover, we propose a coarse-to-fine strategy for calculating both sentence-level and word-level similarity scores, to further enhance retrieval and filter out irrelevant details. Our approach achieves a 3.7% absolute improvement over state-of-the-art methods on RETVQA and a 14.5% improvement over CLIP. Comprehensive experiments and detailed ablation studies demonstrate the superiority of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Revisiting the efficacy of weak consistencies: a study of forward checking

引用

Science China(Information Sciences) 2021年第7期64卷 233-235页

作者： Zhe LI Zhezhou YU Hongbo LI Jinsong GUO Zhanshan LI Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University College of Information Science and Technology Northeast Normal University Department of Computer Science University of Oxford

Dear editor,Arc consistency (AC)[1] is currently the most popular local consistency for solving constraint satisfaction problems(CSP). To solve CSPs more efficiently, extensive work [2–4]has been done to find local c... 详细信息

关键词： Information Systems and Communication Service

来源：评论

学校读者我要写书评

暂无评论

Acupuncture and Tuina knowledge Graph for Ancient Literature of Traditional Chinese Medicine

Acupuncture and Tuina Knowledge Graph for Ancient Literature...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaosong Han Xiaoran Li Yanchun Liang Xinghao Wang Dong Xu Renchu Guan Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Software Jilin University Changchun China Christopher S. Bond Life Sciences Center University of Missouri Columbia USA

ISBN: (纸本)9781665429825

The Traditional Chinese Medicine’s ancient literature recorded the massive medical theories and abundant medical experiences. To better understand and utilize, the knowledge from the literature, the Acupuncture and Tuina knowledge Graph is proposed in this paper. Meanwhile, a deep learning network is established for acupuncture and tuina-related entity recognition and entity-relationship extraction. Finally, the trained network is able to reach an 82%+ F1-score for NER and 70%+ F1-score for relationship extraction.

关键词： Deep learning Conferences Labeling Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Drive: An Adjustable Parallel Architecture Based on Evidence Awareness for Fake News Detection

SSRN

引用

SSRN 2024年

作者： Cong, Mou Liu, Lu Han, Jiayu Zhu, Beibei Yuan, Xiaosong Peng, Tao College of Computer Science and Technology Jilin University 2699 Qianjin Street Jilin Changchun130012 China College of Software Jilin University 2699 Qianjin Street Jilin Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University 2699 Qianjin Street Jilin Changchun130012 China Department of Linguistics University of Washington SeattleWA98195 United States

Fake news detection becomes a critical challenge in NLP. Batch processing with attention-derivative models is a popular solution for fake news detection. Models with attention mechanisms could mitigate the long-distance dependence problem. However, we find that extracting local dependencies using convolutional networks is as important as extracting global dependencies using attention mechanisms. Besides, fake news datasets often suffer from problems such as imbalance and are hard to understand by current models. To address these problems, we propose DRIVE, which is short for an adjustable parallel architecture based on evidence awareness for fake news detection to alleviate the above problems, in which we introduce Claim as a supporting clue to enhance the model’s comprehension ability. Specifically, we propose a novel method for unbalanced datasets and design adjustable parallel branches, using Claim Additives Network (ClaimAddNet) and the MLP with convolutional gating mechanism (CPMLP) to capture global and local information in distinct branches, respectively. Experiments conducted on 5 public datasets demonstrate that DRIVE outperforms all baselines, improving accuracy by approximately 1.7 %. Furthermore, we implement an anti-noise interference test and evaluate the weighted average of the two branches along with ablation studies. © 2024, The Authors. All rights reserved.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Contrastive Fusion of Generative and Discriminative Lesion Maps for Weakly Supervised Medical Image Segmentation

SSRN

引用

SSRN 2023年

作者： Du, Wei Huo, Yongkang Tang, Shiyi Chen, Liang Li, Ying Li, Gaoyang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China College of Engineering Shantou University Shantou515063 China Translational Medical Center for Stem Cell Therapy Institute for Regenerative Medicine Shanghai East Hospital Bioinformatics Department School of Life Sciences and Technology Tongji University Shanghai200092 China

Medical image segmentation is a crucial computer-aided diagnosis (CAD) procedure in various clinical applications. However, most existing methods rely on pixel-level annotations, which are costly and time-consuming. We propose a novel contrastive fusion model of generative and discriminative lesion maps for weakly supervised medical image segmentation to address this limitation. The generative lesion map is generated by a lesion region-guided cycle-consistent adversarial network (CCANet), and the discriminative lesion map is produced by a class-aware-based discriminative lesion localization network (DLLNet). CCANet and DLLNet share weights at the encoder layer, which contains skip connections and channel attention modules to enhance feature embedding. In order to fully utilize and integrate the generative and discriminative lesion maps, and improve the segmentation accuracy, we design a fusion method based on contrastive loss to jointly train CCANet and DLLNet. The final lesion segmentation result is obtained by applying dense conditional random fields (Dense CRF) to the fused lesion map. Extensive experiments on three benchmark medical image datasets show that our model outperforms the state-of-the-art methods on weakly supervised medical image segmentation, especially in datasets with few samples, validating the proposed model's good generalization ability and robustness in various medical image segmentation scenarios. The source code and experiment datasets are available on GitHub: https://***/mlcb-jlu/GDC4MedSeg. © 2023, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Prior-guided dual-stage diabetic retinopathy grading model based on feature collaboration of lesion and vascular structure

引用

Expert Systems with Applications 2025年 285卷

作者： Guo, Xiaoxin Yang, Guangqi Xu, Chenfangqian Dong, Hongliang Hu, Xiaoying Che, Songtian Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University 2699 Qianjin Street Changchun130012 China College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China Ophthalmology Department Bethune First Hospital of Jilin University Changchun Jilin130021 China Ophthalmology Department Bethune Second Hospital of Jilin University Changchun Jilin130041 China

In order to fully utilize lesion features and vascular structure and solve the problem of class imbalance, diabetes retinopathy (DR) grading is modeled as a dual-stage task, and the prior-guided dual-stage diabetes retinopathy grading model is proposed by designing an end-to-end hierarchical framework, consisting of XE-Net and MFC-Net. The former uses vascular structure from color fundus images as prior knowledge to guide the classification of proliferative diabetic retinopathy (PDR) and non-PDR;the latter further classifies non-PDR images using color fundus images with four types of segmented lesions. The core of MFC-Net is the feature collaboration block (FCB) for multi-classification tasks, which is proposed to facilitate effective collaboration between global and local features. In addition, a class-balanced (CB) loss weight is also introduced to address the common class imbalance problem in DR datasets. The experimental results on two publicly available datasets, DDR and IDRiD show that the proposed model has significant advantages. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Meta-path-based outlier detection in heterogeneous information network

引用

Frontiers of Computer Science 2020年第2期14卷 388-403页

作者： Lu LIU Shang WANG Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun 130012China College of Software Jilin UniversityChangchun 130012China College of Computer Science and Technology Jilin UniversityChangchun 130012China College of Communication Engineering Jilin UniversityChangchun 130012China Department of Computer Science New Jersey Institute of TechnologyUniversity HeightsNewark NJ 07102USA

Mining outliers in heterogeneous networks is crucial to many applications,but challenges *** this paper,we focus on identifying meta-path-based outliers in heterogeneous information network(HIN),and calculate the similarity between different types of *** propose a meta-path-based outlier detection method(MPOutliers)in heterogeneous information network to deal with problems in one go under a unified *** calculates the heterogeneous reachable probability by combining different types of objects and their *** discovers the semantic information among nodes in heterogeneous networks,instead of only considering the network *** also computes the closeness degree between nodes with the same type,which extends the whole heterogeneous ***,each node is assigned with a reliable weighting to measure its authority *** experiments on two real datasets(AMiner and Movies dataset)show that our proposed method is very effective and efficient for outlier detection.

关键词： data mining heterogeneous information network outlier detection short text similarity

来源：评论

学校读者我要写书评

暂无评论

A surrogate model based genetic algorithm for complex problem solving 6

A surrogate model based genetic algorithm for complex proble...

引用

6th Annual International Conference on Network and Information Systems for Computers, ICNISC 2020

作者： Pei, Ying Gao, Hao Han, Xiaosong College of Information Engineering Changchun University of Finance and Economics Changchun130122 China Key Laboratory for Symbol Computation Knowledge Engineering of National Education Ministry College of Computer Science and Technology College of Software Jilin University Changchun130012 China

It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely huge. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem, to reduce the number of actual calculated fitness values. In this paper, BP neural network, the least square method and support vector machine were fused in the genetic algorithm to evaluate partial individuals' fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the calculating counts of fitness function on similar accuracy basis compared with simple genetic algorithm. © 2020 Journal of Physics: Conference Series.

关键词： Genetic algorithms

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：