检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhang, Yi Sang, Jitao Wang, Junyang Jiang, Dongmei Wang, Yaowei School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China Peng Cheng Lab Shenzhen China

Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking, and criminal justice. Existing work tackles this issue by minimizing the employed information about social attributes in models for debiasing. However, the high correlation between target task and these social attributes makes learning on the target task incompatible with debiasing. Given that model bias arises due to the learning of bias features (i.e., gender) that help target task optimization, we explore the following research question: Can we leverage shortcut features to replace the role of bias feature in target task optimization for debiasing? To this end, we propose Shortcut Debiasing, to first transfer the target task's learning of bias attributes from bias features to shortcut features, and then employ causal intervention to eliminate shortcut features during inference. The key idea of Shortcut Debiasing is to design controllable shortcut features to on one hand replace bias features in contributing to the target task during the training stage, and on the other hand be easily removed by intervention during the inference stage. This guarantees the learning of the target task does not hinder the elimination of bias features. We apply Shortcut Debiasing to several benchmark datasets, and achieve significant improvements over the state-of-the-art debiasing methods in both accuracy and fairness. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

SEMANTICALLY CONSISTENT VIDEO-TO-AUDIO GENERATION USING MULTIMODAL LANGUAGE LARGE MODEL

arXiv

引用

arXiv 2024年

作者： Chen, Gehui Wang, Guan'an Huang, Xiaowen Sang, Jitao School of Computer Science and Technology Beijing Jiaotong University China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China Ministry of Education China

Existing works have made strides in video generation, but the lack of sound effects (SFX) and background music (BGM) hinders a complete and immersive viewer experience. We introduce a novel semantically consistent video-to-audio generation framework, namely SVA, which automatically generates audio semantically consistent with the given video content. The framework harnesses the power of multimodal large language model (MLLM) to understand video semantics from a key frame and generate creative audio schemes, which are then utilized as prompts for text-to-audio models, resulting in video-to-audio generation with natural language as an interface. We show the satisfactory performance of SVA through case study and discuss the limitations along with the future research direction. The project page is available at https://***/***/. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential of Reverse Distillation for Anomaly Detection 39

Unlocking the Potential of Reverse Distillation for Anomaly ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Xinyue Wang, Jianyuan Leng, Biao Zhang, Shuo School of Computer Science and Engineering Beihang University China School of Intelligence Science and Technology University of Science and Technology Beijing China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer & Technology Beijing Jiaotong University China

ISBN: (纸本)157735897X

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network’s over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To address this problem, the widely accepted Reverse Distillation (RD) paradigm designs the asymmetry teacher and student, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student’s ability to generate normal features and optimizes the teacher’s differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD’s potential. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net

Semantic-Preserving Abstractive Text Summarization with Siam...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Jiang, Deqiang Ren, Bo School of Computer Science and Technology University of Science and Technology of China. China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China IFLYTEK Co. Ltd. China Tencent Youtu Lab China

ISBN: (纸本)9781955917766

We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text. Different from previous generative adversarial net based methods, SSPGAN is equipped with a siamese semanticpreserving discriminator, which can not only be trained to discriminate the machine-generated summaries from the human-summarized ones, but also ensure the semantic consistency between the source text and target summary. As a consequence of the min-max game between the generator and the siamese semantic-preserving discriminator, the generator can generate a summary that conveys the key content of the source text more accurately. Extensive experiments on several text summarization benchmarks in different languages demonstrate the effectiveness of the proposed method. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AutoRG: An automatic report generation framework for Large and small model collaboration 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Zhang, Jing Shu, Jiangming Zhang, Yuxiang Wu, Bin Wang, Wei Yu, Jian Sang, Jitao School of Computer Science and Technology Beijing Jiaotong University Beijing China Lab of Traffic Dala Analysis and Mining Beijing China Suwen Data Intelligent Technology Co. LTD. Shenzhen China

ISBN: (纸本)9780000000002

Automatic report generation technology has demonstrated enormous potential in saving human resources and enhancing work efficiency. With the introduction of large-scale artificial intelligence models, the fluency and interpretability of generated reports have been significantly improved. However, current automatic report generation still requires manual completion, lacking flexibility and richness. Moreover, errors or redundancies in the outputs of small models, along with the inherent randomness of large models, can result in the lack of stability in report content. This paper introduces AutoRG, an integrated framework designed for automated report generatio, to reduce human intervention by leveraging the understanding and planning capabilities of large models, consequently enriching the depth of generated reports. Additionally, it incorporates an information correction and content iteration mechanism to diminish reliance on the outputs of small models and mitigate the impact of randomness inherent in large models. To evaluate the eicacy of the AutoRG framework comprehensively, we conducted experiments focusing on the automated generation of patent technology reports. Our evaluation approach across various dimensions, ensuring a thorough examination of AutoRG's performance. The results indicate significant advantages of the framework in improving the richness and stability of report generation. © 2024 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Detecting Community Through User Similarity analysis on Twitter

Detecting Community Through User Similarity Analysis on Twit...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Md Ahsan Ul Hasan Azuraliza Abu Bakar Mohd Ridzwan Yaakub Sentiment Analysis Lab Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Malaysia Data Mining and Optimization Lab Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Malaysia

Community detection in social relationship networks is a significant research domain within the field of social network analysis. However, Twitter sets itself apart from conventional friends’ and followers’ networks due to its users’ distinct focus on sharing thoughts and ideas related to specific topics rather than prioritising personal connections. As a result, relying solely on friends’ and followers’ relations in Twitter networks for community detection would be insufficient and incomplete. In this paper, we proposed a Twitter community detection method that measures similarity using user profiles, tweet subjects, and tweet sentiment in this research. We constructed a similarity network using real-time Twitter API data and compared it to Zachary's Karate Network. The proposed approach enhances the quality function of modularity and conductance in the Louvain community detection algorithm, resulting in a more precise and meaningful community structure within the Twitter network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction

TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescr...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhou, Xingzhi Dong, Xin Li, Chunhao Bai, Yuning Xu, Yulong Cheung, Ka Chun Se, Simon Song, Xinpeng Zhang, Runshun Zho, Xuezhong Zhang, Nevin L. Hong Kong University of Science and Technology Department of Computer Science and Technology Hong Kong Hong Kong Beijing Jiaotong University Institute of Medical Intelligence Department of Artificial Intelligence Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing100044 China China Academy of Chinese Medical Sciences Guang'anmen Hospital Beijing China Henan University of Chinese Medicine School of Information Technology China Nvidia Nvaitc Hong Kong Hong Kong Nvidia Nvaitc Singapore

ISBN: (纸本)9798350386226

Traditional Chinese medicine (TCM) has relied on specific combinations of herbs in prescriptions to treat various symptoms and signs for thousands of years. Predicting TCM prescriptions poses a fascinating technical challenge with significant practical implications. However, this task faces limitations due to the scarcity of high-quality clinical datasets and the complex relationship between symptoms and herbs. To address these issues, we introduce DigestDS, a novel dataset comprising practical medical records from experienced experts in digestive system diseases. We also propose a method, TCM-FTP (TCM Fine-Tuning Pre-trained), to leverage pre-trained large language models (LLMs) via supervised fine-tuning on DigestDS. Additionally, we enhance computational efficiency using a low-rank adaptation technique. Moreover, TCM-FTP incorporates data augmentation by permuting herbs within prescriptions, exploiting their order-agnostic nature. Impressively, TCM-FTP achieves an F1-score of 0.8031, significantly outperforming previous methods. Furthermore, it demonstrates remarkable accuracy in dosage prediction, achieving a normalized mean square error of 0.0604. In contrast, LLMs without fine-tuning exhibit poor performance. Although LLMs have demonstrated wide-ranging capabilities, our work underscores the necessity of fine-tuning for TCM prescription prediction and presents an effective way to accomplish this. © 2024 IEEE.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

DenoiseRep: denoising model for representation learning 24

DenoiseRep: denoising model for representation learning

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhengrui Xu Guan'an Wang Xiaowen Huang Jitao Sang School of Computer Science and Technology Beijing Jiaotong University School of Computer Science and Technology Beijing Jiaotong University and Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University and Key Laboratory of Big Data & Artificial Intelligence in Transportation(Beijing Jiaotong University) Ministry of Education

ISBN: (纸本)9798331314385

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors" [4]. In this paper, we propose a novel Denoising Model for Representation Learning (DenoiseRep) to improve feature discrimination with joint feature extraction and denoising. DenoiseRep views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, DenoiseRep fus es the parameters of feature extraction and denoising layers, and theoretically demonstrates its equivalence before and after the fusion, thus making feature denoising computation-free. DenoiseRep is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures. Code is available at https://***/wangguanan/DenoiseRep.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scenario-aware Multimodal Chain-of-Thought Prompting for Rationales of Video Social Relations

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Qin, Penggang Xu, Tong Zhang, Chao Wang, Heda Hu, Yao Chen, Enhong University of Science and Technology of China Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science Hefei 230026 China Xiaohongshu China

Recently, audiences have increasingly watched diverse dramas and movies on streaming platforms, prompting platform administrators to enhance their understanding of video semantics. In particular, capturing and interpreting social relations among characters is critical for content-driven intelligent services and enhancing user experience. However, most existing research has solely approached social relations recognition as a classification problem, without justifiable interpretation of prediction results within the video context. To address this issue, we study cognitive science research and the Chain-of-Thought (CoT) strategy. Based on these foundations, we propose SaMo-CoT, an approach that leverages large language models (LLMs) in step-by-step reasoning. This approach simulates human cognitive processes by combining social scenarios in videos and incorporating empirical social interaction knowledge. In this way, we enable verbal rationales for determining social relations in video understanding. Furthermore, we present an innovative doubly-right social relation recognition framework that predicts both correct social relation labels and correct scenario rationales. Specifically, we translate verbal CoT into multimodal CoT by leveraging scenario-aware prompts and contrastive learning. Extensive experiments demonstrate significant improvements in classification accuracy and interpretability compared to traditional approaches. © 1991-2012 IEEE.

关键词： Chain of thoughts Large language models Social relationship recognition Video understanding

来源：评论

学校读者我要写书评

暂无评论

WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models

WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark f...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jian Liu Kangyun Ning Yisong Su Wenjuan Han Jinan Xu Yuanzhe Zhang University of Science and Technology Beijing Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China College of Computer and Data Science Fuzhou University Fuzhou China National Science Library Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Although Large Language Models (LLMs) excel in NLP tasks, they still need external tools to extend their ability. Current research on tool learning with LLMs often assumes mandatory tool use, which does not always align with real-world situations, where the necessity for tools is uncertain, and incorrect or unnecessary use of tools can damage the general abilities of LLMs. Therefore, we propose to explore whether LLMs can discern their ability boundaries and use tools flexibly. We then introduce the Whether-or-not tool usage Evaluation benchmark (WTU-Eval) to assess LLMs with eleven datasets, where six of them are tool-usage datasets, and five are general datasets. LLMs are prompted to use tools according to their needs. The results of eight LLMs on WTU-Eval reveal that LLMs frequently struggle to determine tool use in general datasets, and LLMs’ performance in tool-usage datasets improves when their ability is similar to ChatGPT.

关键词： Large language models Benchmark testing Signal processing Chatbots Acoustics Speech processing

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：