检索结果-内蒙古大学图书馆

24th IEEE International Conference on data Mining Workshops, ICDMW 2024

作者： Ong, Keane Mao, Rui Varshney, Deeksha Satapathy, Ranjan Cambria, Erik Mengaldo, Gianmarco National University of Singapore Asian Institute of Digital Finance Singapore Nanyang Technological University College of Computing and Data Science Singapore National University of Singapore College of Design & Engineering Singapore Agency for Science Technology and Research Institute of High Performance Computing Singapore

ISBN: (纸本)9798331530631

This research involves examining whether sentiment on climate change can be accounted as a systematic risk factor within sustainable finance. Tweets related to climate change from 2014-2022 are collected via the Twitter API. RoBERTa is then deployed to label the collected tweets according to sentiment polarity. Thereafter, DistilBERT is utilised to classify tweets according to their different climate change topics Aggregated, Impact, Politics &icy, Mitigation, Rootcause. Using these sentiment and topic labels, monthly sentiment scores are aggregated from the frequency of sentiment polarity (number of positive, and negative tweets), and segmented according to the topics that the tweets are classified under. On the other hand, we collect the monthly returns of various green ETFs, alongside ETFs that contain stocks from other sectors (technology, oil and gas), as well as 2 baskets of stocks (sustainable and heavy-polluting). We run Fama-French regressions by conducting time series regression of monthly returns on the traditional 3 factors, with specific addition of sentiment scores. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

OL4TeX: Adaptive Online Learning for Text Classification under Distribution Shifts

OL4TeX: Adaptive Online Learning for Text Classification und...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Kim, Min-Seon Liu, Ling Kwon, Hyuk-Yoon Seoul National University of Science and Technology Graduate School of Data Science Seoul Korea Republic of Georgia Institute of Technology College of Computing AtlantaGA United States

ISBN: (纸本)9798350362480

This study presents an adaptive online learning method for text classification under distribution shifts. We formulate a typical neural network-based text classification model as multiple logical modules. By leveraging the characteristics of the modules, we introduce three novel indicators to effectively measure the degree of dynamic distribution shifts without evaluating the model. To enhance online learning, we tactically trade off between learning efficiency and accuracy based on distribution shifts measured in real time. To the best of our knowledge, this is the first effort to adapt the model to the preference of learning efficiency or accuracy for online text classification. Extensive experiments on real-world streaming text datasets show that our method outperforms the best static update strategy and state-of-the-art online text classification models. Our code and data are available at https://***/bigbases/online-learning-text. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Conversational Explanations: Discussing Explainable AI with Non-AI Experts 25

Conversational Explanations: Discussing Explainable AI with ...

引用

30th International Conference on Intelligent User Interfaces, IUI 2025

作者： Zhang, Tong Zhang, Mengao Low, Wei Yan Yang, X. Jessie Li, Boyang Albert College of Computing and Data Science Nanyang Technological University Singapore Singapore Nanyang Technological University Singapore Singapore College of Engineering University of Michigan Ann ArborMI United States

ISBN: (纸本)9798400713064

Explainable AI (XAI) aims to provide insights into the decisions made by AI models. To date, most XAI approaches provide only one-time, static explanations, which cannot cater to users' diverse knowledge levels and information needs. Conversational explanations have been proposed as an effective method to customize XAI explanations. However, building conversational explanation systems is hindered by the scarcity of training data. Training with synthetic data faces two main challenges: lack of data diversity and hallucination in the generated data. To alleviate these issues, we introduce a repetition penalty to promote data diversity and exploit a hallucination detector to filter out untruthful synthetic conversation turns. We conducted both automatic and human evaluations on the proposed system, fEw-shot Multi-round ConvErsational Explanation (EMCEE). For automatic evaluation, EMCEE achieves relative improvements of 81.6% in BLEU and 80.5% in ROUGE compared to the baselines. EMCEE also mitigates the degeneration of data quality caused by training on synthetic data. In human evaluations (N = 60), EMCEE outperforms baseline models and the control group in improving users' comprehension, acceptance, trust, and collaboration with static explanations by large margins. Through a fine-grained analysis of model responses, we further demonstrate that training on self-generated synthetic data improves the model's ability to generate more truthful and understandable answers, leading to better user interactions. To the best of our knowledge, this is the first conversational explanation method that can answer free-form user questions following static explanations. © 2025 Copyright held by the owner/author(s).

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

RevMUX: data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference

RevMUX: Data Multiplexing with Reversible Adapters for Effic...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Xu, Yige Guo, Xu Zeng, Zhiwei Miao, Chunyan Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly Singapore College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Large language models (LLMs) have brought a great breakthrough to the natural language processing (NLP) community, while leading the challenge of handling concurrent customer queries due to their high throughput demands. data multiplexing addresses this by merging multiple inputs into a single composite input, allowing more efficient inference through a shared forward pass. However, as distinguishing individuals from a composite input is challenging, conventional methods typically require training the entire backbone, yet still suffer from performance degradation. In this paper, we introduce RevMUX, a parameter-efficient data multiplexing framework that incorporates a reversible design in the multiplexer, which can be reused by the demultiplexer to perform reverse operations and restore individual samples for classification. Extensive experiments on four datasets and three types of LLM backbones demonstrate the effectiveness of RevMUX for enhancing LLM inference efficiency while retaining a satisfactory classification performance. © 2024 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Historical Test-time Prompt Tuning for Vision Foundation Models 38

Historical Test-time Prompt Tuning for Vision Foundation Mod...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Jingyi Huang, Jiaxing Zhang, Xiaoqin Shao, Ling Lu, Shijian College of Computing and Data Science Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University of Technology China UCAS-Terminus AI Lab University of Chinese Academy of Sciences China

Test-time prompt tuning, which learns prompts online with unlabelled test samples during the inference stage, has demonstrated great potential by learning effective prompts on-the-fly without requiring any task-specific annotations. However, its performance often degrades clearly along the tuning process when the prompts are continuously updated with the test data flow, and the degradation becomes more severe when the domain of test samples changes continuously. We propose HisTPT, a Historical Test-time Prompt Tuning technique that memorizes the useful knowledge of the learnt test samples and enables robust test-time prompt tuning with the memorized knowledge. HisTPT introduces three types of knowledge banks, namely, local knowledge bank, hard-sample knowledge bank, and global knowledge bank, each of which works with different mechanisms for effective knowledge memorization and test-time prompt optimization. In addition, HisTPT features an adaptive knowledge retrieval mechanism that regularizes the prediction of each test sample by adaptively retrieving the memorized knowledge. Extensive experiments show that HisTPT achieves superior prompt tuning performance consistently while handling different visual recognition tasks (e.g., image classification, semantic segmentation, and object detection) and test samples from continuously changing domains. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

APPLICATION OF GENERATIVE ARTIFICIAL INTELLIGENCE FOR EPIDEMIC MODELING

APPLICATION OF GENERATIVE ARTIFICIAL INTELLIGENCE FOR EPIDEM...

引用

2024 Winter Simulation Conference, WSC 2024

作者： Villaplana, Hannah Danielle Ladera Kwak, Jaeyoung Lees, Michael H. Li, Hongying Cai, Wentong College of Computing and Data Science Nanyang Technological University Singapore Singapore Informatics Institute University of Amsterdam Amsterdam Netherlands Department of Fluid Dynamics Institute of High Performance Computing Singapore Singapore

ISBN: (纸本)9798331534202

Epidemic models have become increasingly useful, especially in the wake of the recent COVID-19 pandemic, emphasizing the crucial role of human behavior in the spread of disease. There has been a recent rise in the usage and popularity of generative artificial intelligence (GenAI), such as ChatGPT especially with its ability to mimic human behavior. In this study, we demonstrate a novel application of GenAI for epidemic modeling. We employed GenAI for creating agents living in a hypothetical town in simulations and simulating their behavior within the context of an ongoing pandemic. We performed a series of simulations to quantify the impact of agent traits and the availability of information for health condition, virus, and government guidelines on the disease spread patterns in terms of peak time and epidemic duration. We also characterized the most influential factors in agents’ decision-making using random forest model. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

RADF: Architecture decomposition for function as a service

RADF: Architecture decomposition for function as a service

引用

作者： Zhu, Lulai Tamburri, Damian Andrew Casale, Giuliano Department of Computing Imperial College London London United Kingdom Jheronimus Academy of Data Science Eindhoven University of Technology ‘s-Hertogenbosch Netherlands

As the most successful realization of serverless, function as a service (FaaS) brings in a novel cloud computing paradigm that can save operating costs, reduce management effort, enable seamless scalability, and augment development productivity. Migration of an existing application to the serverless architecture is, however, an intricate task as a great number of decisions need to be made along the way. We propose in this paper RADF, a semi-automatic approach that decomposes a monolith into serverless functions by analyzing the business logic inherent in the interface of the application. The proposed approach adopts a two-stage refactoring strategy, where a coarse-grained decomposition is performed at first, followed by a fine-grained one. As such, the decomposition process is simplified into smaller steps and adaptable to generate a solution at either microservice or function level. We have implemented RADF in a holistic DevOps methodology and evaluated its capability for microservice identification and feasibility for code refactoring. In the evaluation experiments, RADF achieves lower coupling and relatively balanced cohesion, compared to previous decomposition approaches. © 2023 The Authors. Software: Practice and Experience published by John Wiley & Sons Ltd.

关键词： Operating costs

来源：评论

学校读者我要写书评

暂无评论

Seg-diffusion: Text-to-Image Diffusion Model for Open-Vocabulary Semantic Segmentation

Seg-diffusion: Text-to-Image Diffusion Model for Open-Vocabu...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Shuo Huang, Jiaming Wu, Yan Hu, Tao Tang, Wenbing Liu, Jing Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Huolala Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798350368741

Open-vocabulary semantic segmentation (OVSS) is a challenging computer vision task that labels each pixel within an image based on text descriptions. Recent advancements in OVSS are largely attributed to the increased model capacity. However, these models often struggle with unfamiliar images or unseen text, as their visual language understanding is limited to training data. Text-to-image (T2I) diffusion models have demonstrated strong image generation with diverse open-vocabulary descriptions. It prompted us to explore whether the comprehensive priors in T2I diffusion models could enhance the zero-shot generalization of OVSS. In this study, we define OVSS as a denoising diffusion task from noisy to object mask and introduce Seg-diffusion, a novel method based on Stable Diffusion that utilizes its extensive visual and linguistic prior knowledge. Specifically, the object mask diffuses from ground-truth to a random distribution in latent space. The model learns to reverse this noisy process to reconstruct object mask to segment objectives using text embeddings with our proposed Content Attention Module (CAM). Extensive experiments on popular OVSS benchmarks show that Seg-diffusion outperforms previous well-established methods and achieves impressive zero-shot generalization to unseen datasets. © 2025 IEEE.

关键词： content attention module fine-tuning protocol open-vocabulary semantic segmentation text-to-image LDM

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Method to Measure Distribution Consistency of Mixed-Attribute datasets

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 182-196页

作者： He, Yulin Ye, Xuan Huang, Defa Fournier-Viger, Philippe Huang, Joshua Zhexue College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Random sample partition (RSP) is a newly developed data management and processing model for Big data processing and analysis. To apply the RSP model for Big data computation tasks, it is very important to measure the distribution consistency of different datasets. Existing measurement methods for continuous-attribute and discrete-attribute datasets cannot directly deal with mixed-attribute datasets. In this article, we design a hybrid method to measure the distribution consistency among different mixed-attribute datasets by using a multilayer extreme learning machine (MLELM) and the generalized maximum mean discrepancy (GMMD) criterion, abbreviated as MLELM-GMMD. MLELM is first used to transform original mixed-attribute datasets into corresponding deep encoding datasets. Then, the GMMD criterion is applied to check the distribution consistency of the deep encoding datasets. Four experiments have been done to validate the feasibility and effectiveness of MLELM-GMMD, i.e., the impact of MLELM on the amount of information during mixed-attribute data transformation, the impact of MLELM on distributions of mixed-attribute data, the distribution consistencies of RSP and non-RSP data blocks, and the comparison with other measurement methods. Experimental results show that the proposed MLELM-GMMD method can measure the distribution consistency of mixed-attribute datasets more accurately than one-hot encoding-based methods. © 2022 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Application of Bayes Rule for Precise Analysis of Class-Imbalanced Stroke data

Application of Bayes Rule for Precise Analysis of Class-Imba...

引用

2023 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Viswapriya, S.E. Rajeswari, D. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Data Science and Business Systems Kattankulathur Chennai India

ISBN: (纸本)9798350319200

The interpretability of stroke risk prediction is still lagging and it can be solved by using deep analysisofdata with the application of the Bayes rule. The prediction model has to be produced with accuracy, clarity, and comprehensibility without ambiguity, especially in machine learning and data analytics. The class imbalance problem is a common issue affecting the raw data, which means the imbalanced categorization of outcome feature value. In many fields, such as fraud detection, network intrusion detection, and medical diagnostics, this class imbalance issue is present where negative class samples outnumber positive class samples. If some datasets have class imbalance and imperfect issues, there will be no proper classification pattern. There are many resampling methods to address this class imbalance problem. However, these resampling methods can make an even distribution of classes by generating or omitting some samples, but theycannot handle imperfect data. The probabilistic analysis can lead to the identification of issues that exist in the dataset and provide direction to medical experts on dealing with the condition to avoid *** strength of applying the Bayes rule will provide a meaningful interpretation of stroke data. This paper investigates the Baye rule's significance in stroke data analysis. © 2023 IEEE.

关键词： Bayes rule Class imbalance probabilistic analysis Resampling Stroke data

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：