检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Mingkun Bi, Keping Chen, Wei Chen, Quanrun Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of AI Safety Institute of Computing Technology CAS China Key Laboratory of Network Data Science and Technology Institute of Computing Technology CAS China School of Statistics University of International Business and Economics China

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://***/CAS-AISafetyBasicResearchGroup/CausalDiff. © 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

GHVC-Net: Hypervolume Contribution Approximation Based on Graph Neural Network

GHVC-Net: Hypervolume Contribution Approximation Based on Gr...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wu, Guotong Nan, Yang Shang, Ke Ishibuchi, Hisao Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9781665410205

This paper proposes a framework called GHVC-Net that uses the graph neural network (GNN) model to approximate each solution's hypervolume contribution (HVC). GHVC-Net is permutation invariant and can handle solution sets of arbitrary size, similar to the properties of GNN. Compared to HVC-Net (i.e., a machine learning model for HVC approximation), GHVC-Net achieves better accuracy with less training time. GHVC-Net is also compared with traditional approximation methods, such as line-based and point-based methods, to demonstrate its ability to identify the solution with the smallest (largest) HVC. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Generating Apoptosis-Inducing Anticancer Peptides Targeting BCL-xL Using Latent Diffusion Models on Small datasets

Generating Apoptosis-Inducing Anticancer Peptides Targeting ...

引用

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

作者： Tiara Natasha Binte Sayuti Wang Conghao Jagath C Rajapakse College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The overexpression of B-cell lymphoma-extra large (BCL-xL), an anti-apoptotic protein, plays a pivotal role in various cancers by inhibiting apoptosis and promoting tumor progression. We introduce Latent Diffusion Model (LDM) specifically designed to generate apoptosis-inducing Anticancer Peptides (ACPs) targeting BCL-xL. By applying a diffusion process to high-dimensional embeddings generated by ESM-2, a state-of-the-art Protein Language Model (PLM), our approach successfully generates peptides with optimal physicochemical properties, even when trained on a relatively small dataset. In comparison to Variational Autoencoder (VAE) and Wasserstein Autoencoder (WAE), our architecture not only mitigates the limitations associated with small datasets but also produces peptides that closely align with desired physiochemical properties. Evaluation against key metrics—molecular weight, isoelectric point, net charge at pH 7, grand average of hydropathy, instability index, and anticancer peptide score,demonstrates that our model consistently outperforms both VAE and WAE, offering a promising strategy for the development of novel anticancer therapies.

关键词： Proteins Peptides Computational modeling Autoencoders Medical treatment Signal processing Diffusion models Structural engineering Speech processing Tumors

来源：评论

学校读者我要写书评

暂无评论

Decoding Brain Structure and Gene Expression Interactions in Alzheimer’s Disease Pathology

Decoding Brain Structure and Gene Expression Interactions in...

引用

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

作者： Amashi Niwarthana Chockalingam Kasi Yi Hao Chan Conghao Wang Jagath C Rajapakse College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Although brain imaging has provided crucial insights into Alzheimer’s disease (AD) progression, its limitations in capturing molecular changes have motivated the need to integrate and interpret transcriptomic data, which can reveal early-stage molecular disruptions. By interpreting both structural and gene expression patterns, there is potential to gain a more comprehensive understanding of the disease and identify interactions that drive AD pathogenesis. This study introduces a novel deep learning framework that integrates structural magnetic resonance imaging (sMRI) and gene expression (GE) data for AD prediction. The model extracts features from both data modalities and employs a novel approach to quantify cross-modal interactions. Our multimodal architecture achieves 83.6% accuracy in AD prediction, demonstrating its effectiveness in combining imaging and transcriptomic data. We present a technique for interpreting interactions between specific brain regions and gene expression patterns, providing insights into their joint contribution to AD risk. This approach enables the identification of both established and potential new AD biomarkers, spanning structural brain changes and transcriptomic alterations. By offering a deeper understanding of AD’s molecular and structural aspects, our work advances the field of multimodal biomarker discovery in neurodegenerative diseases and paves the way for more comprehensive early diagnosis strategies.

关键词： Pathology Magnetic resonance imaging Transcriptomics Biomarkers Feature extraction Brain modeling data models Decoding Gene expression Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Reputation-aware Revenue Allocation for Auction-based Federated Learning 39

Reputation-aware Revenue Allocation for Auction-based Federa...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Tang, Xiaoli Yu, Han College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Auction-based Federated Learning (AFL) has gained significant research interest due to its ability to incentivize data owners (DOs) to participate in FL model training tasks of data consumers (DCs) through economic mechanisms via the auctioneer. One of the critical research issues in AFL is decision support for the auctioneer. Existing approaches are based on the simplified assumption of a single, monopolistic AFL marketplace, which is unrealistic in real-world scenarios where multiple AFL marketplaces can co-exist and compete for the same pool of DOs. In this paper, we relax this assumption and frame the AFL auctioneer decision support problem from the perspective of helping them attract participants in a competitive AFL marketplace environment while safeguarding profit. To achieve this objective, we propose the Auctioneer Revenue Allocation Strategy for AFL (ARAS-AFL). We design the concepts of the attractiveness and competitiveness from the perspective of autioneer reputation. Based on the Lyapunov optimization, ARAS-AFL helps individual AFL auctioneer achieve the dual objective of balancing the reputation management costs and its own profit by designing a dynamic revenue allocation strategy. It takes into account both the auctioneer’s revenue and the changes in the number of participants on the AFL marketplace. Through extensive experiments on widely used benchmark datasets, ARAS-AFL demonstrates superior performance compared to state-of-the-art approaches. It outperforms the best baseline by 49.06%, 98.69%, 10.32%, and 4.77% in terms of total revenue, number of data owners, public reputation and accuracy of federated learning models, respectively. Copyright © 2025, Association for the Advancement of Artificia Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Open-vocabulary object detection via language hierarchy 24

Open-vocabulary object detection via language hierarchy

引用

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

作者： Jiaxing Huang Jingyi Zhang Kai Jiang Shijian Lu College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798331314385

Recent studies on generalizable object detection have attracted increasing attention with additional weak supervision from large-scale datasets with image-level labels. However, weakly-supervised detection learning often suffers from image-to-box label mismatch, i.e., image-level labels do not convey precise object information. We design Language Hierarchical Self-training (LHST) that introduces language hierarchy into weakly-supervised detector training for learning more generalizable detectors. LHST expands the image-level labels with language hierarchy and enables co-regularization between the expanded labels and self-training. Specifically, the expanded labels regularize self-training by providing richer supervision and mitigating the image-to-box label mismatch, while self-training allows assessing and selecting the expanded labels according to the predicted reliability. In addition, we design language hierarchical prompt generation that introduces language hierarchy into prompt generation which helps bridge the vocabulary gaps between training and testing. Extensive experiments show that the proposed techniques achieve superior generalization performance consistently across 14 widely studied object detection datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving key challenges in collider physics with foundation models

引用

Physical Review D 2025年第5期111卷 L051504-L051504页

作者： Vinicius Mikuni Benjamin Nachman National Energy Research Scientific Computing Center Berkeley Lab Berkeley California 94720 USA Physics Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA Berkeley Institute for Data Science University of California Berkeley California 94720 USA

Foundation models are neural networks that are capable of simultaneously solving many problems. Large language foundation models like ChatGPT have revolutionized many aspects of daily life, but their impact for science is not yet clear. In this paper, we use a new foundation model for hadronic jets to solve three key challenges in collider physics. In particular, we show how experiments can (1) save significant computing power when developing reconstruction algorithms, (2) perform a complete uncertainty quantification for high-dimensional measurements, and (3) search for new physics with model agnostic methods using low-level inputs. In each case, there are significant computational or methodological challenges with current methods that limit the science potential of deep learning algorithms. By solving each problem, we take jet foundation models beyond proof-of-principle studies and into the toolkit of practitioners.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vehicle Insurance Damage Estimation Using YOLOv5 4

Vehicle Insurance Damage Estimation Using YOLOv5

引用

4th International Conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Subash, R. Prathaban, Banu Priya Ganeshkumar, N. Gopinathan, S. School of Computing Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India School of Computing Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur Chennai India Department of Computer Science and Engineering Gitam School of Technology Bengaluru Off-Campus Karnataka Bengaluru562163 India Sri Sai Ram Institute of Technology Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331508845

Accident assessments for insurance companies are currently conducted manually, which can be time-consuming and prone to human error. The proposed method seeks to automate this process, aiming to save time and enhance accuracy. This paper introduces an innovative approach to analyzing object damage by leveraging the advanced YOLOv5 (You Only Look One Level) deep learning architecture. The research is meticulously crafted to address the imperative need for robust and precise detection and classification of damaged objects in images, crucial for effective assessment of structural and environmental integrity. Leveraging the unparalleled real-time object detection capabilities of YOLOv5, the framework is finely tuned and trained on a comprehensive dataset encompassing diverse scenarios of damaged objects. Through exhaustive experimentation and validation, our methodology demonstrates substantial advancements, offering unparalleled efficiency and accuracy in the domain of object damage analysis. The findings of this study hold significant implications for a broad spectrum of applications, ranging from infrastructure monitoring to disaster response, underscoring the transformative potential of deep learning in enhancing critical assessment processes. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Investigation into Theory-Practice Barriers in Sino-New Zealand Undergraduate computing Education 17

A Preliminary Investigation into Theory-Practice Barriers in...

引用

17th International Conference on Computer Supported Education, CSEDU 2025

作者： Dai, Fei Robins, Anthony Peng, Zhihao Huang, Wanni Tan, Chiu-Pih Chen, Tianzhen School of Computing Eastern Institute of Technology Napier New Zealand School of Computing University of Otago Dunedin New Zealand EIT Data Science and Communication College Zhejiang Yuexiu University Zhejiang Shaoxing China

ISBN: (纸本)9789897587467

This paper investigates the barriers hindering the effective transition from theoretical knowledge to practical application in a Sino-New Zealand double-degree undergraduate computing programme. In this unique educational setting, students study at a campus in China but complete both Chinese and New Zealand courses taught jointly by lecturers from both countries. Through a questionnaire administered to these students, we identify critical obstacles such as insufficient foundational knowledge, language barriers, cultural and pedagogical differences, and difficulties adapting to distinct educational systems. Our analysis reveals that these barriers significantly affect students’ academic performance, engagement, and skill development. Based on the findings, we propose targeted interventions, including specialized bridging courses, enhanced language support, refined teaching methods, and improved resource allocation. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Explainable Federated Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Yanci Yu, Han College of Computing and Data Science Nanyang Technological University Singapore

Federated Learning (FL) is a collaborative machine learning paradigm for enhancing data privacy preservation. Its privacy-preserving nature complicates the explanation of the decision-making processes and the evaluation of the reliability of the generated explanations. In this paper, we propose the Uncertainty-aware eXplainable Federated Learning (UncertainXFL) to address these challenges. It generates explanations for decision-making processes under FL settings and provides information regarding the uncertainty of these explanations. UncertainXFL is the first framework to explicitly offer uncertainty evaluation for explanations within the FL context. Explanatory information is initially generated by the FL clients and then aggregated by the server in a comprehensive and conflict-free manner during FL training. The quality of the explanations, including the uncertainty score and tested validity, guides the FL training process by prioritizing clients with the most reliable explanations through higher weights during model aggregation. Extensive experimental evaluation results demonstrate that UncertainXFL achieves superior model accuracy and explanation accuracy, surpassing the current state-of-the-art model that does not incorporate uncertainty information by 2.71% and 1.77%, respectively. By integrating and quantifying uncertainty in the data into the explanation process, UncertainXFL not only clearly presents the explanation alongside its uncertainty, but also leverages this uncertainty to guide the FL training process, thereby enhancing the robustness and reliability of the resulting models. © 2025, CC BY.

关键词： Federated learning

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：