检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Yan Wang, Bin Qu, Xinghua School of Computer Science and Engineering Northeastern University China School of Computing Macquarie University Australia Singapore University of Technology and Design Singapore National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education China Bytedance(Seed) Singapore

ISBN: (纸本)157735897X

Sequential Recommenders (SRs) are trained to predict the next item as the target given its preceding items as the input, assuming every input-target pair is matched and is reliable for training. However, users can be induced by external distractions to click on items inconsistent with their true preferences, resulting in unreliable training instances with mismatched input-target pairs. To resist unreliable data, researchers attempt to develop Robust SRs (RSRs). However, our data analysis unveils that existing RSRs are data-driven. That is, for most instances formed by infrequently co-occurred items, existing RSRs are uncertain about their reliability. To fill this gap, we propose a generic framework - LLM4RSR (Large Language Models for Robust Sequential Recommendation) to semantically complement data-driven RSRs by correcting uncertain instances into reliable ones based on LLMs' semantic comprehension of items beyond co-occurrence. In this way, RSRs can be re-trained with the corrected data for better accuracy. This is a selective knowledge distillation procedure, where the LLM acts as a teacher guiding student RSRs via uncertain instances. To align LLMs with the data correction task and mitigate inherent hallucinations, we equip the LLM with profile, plan, and memory modules, which are automatically optimized via textual gradient descent, eliminating the need for human effort and expertise. Experiments on four real-world datasets spanning eight backbones verify the generality, effectiveness, and efficiency of LLM4RSR. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Limited Label-Support Pavement Damage Segmentation Network with Uniform Rectification and Intrinsic Cross-Dimensional Constraint

SSRN

引用

SSRN 2024年

作者： Yan, Yunhui Wang, Yanyan Song, Kechen Ma, Shuai Huang, Liming Cui, Wenqi School of Mechanical Engineering and Automation Northeastern University Liaoning Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Laboratory of Data Analytics and Optimization for Smart Industry Northeastern University Ministry of Education China

Most recent research on pavement damage segmentation focuses on fully supervised learning to achieve solid performance. The major limitation of this strategy in practice is the heavy reliance on a large number of pixel-level labels, which are labour-intensive and time-consuming to acquire, especially for curvilinear cracks with fine details and inlaid patches with weak edges. This paper proposes a novel methodology to effectively exploit unlabelled data supported by limited label knowledge, thus reducing the heavy annotation burden. The proposed methodology tackles three critical challenges in the pavement damage segmentation based on a semi-supervised paradigm. The first challenge is the noisy pseudo-labels triggered by severely imbalanced prior distributions, which can result in the underutilisation of unlabelled samples. To tackle this challenge, we propose a labelled prior-support uniform rectification module to explicitly improve the prediction quality of pseudo-labels by rectifying their corresponding semantics conditioned on the class-balanced labelled tokens. For the second challenge of the inter-class indistinction, an intrinsic cross-dimensional constraint mechanism is devised to enforce difficult representations to be aligned with the category distribution by the weak vertical constraint within intra-set hierarchical features and the strong parallel cross-set constraint, enabling the model to identify weak texture defects. Finally, an adaptive dual regularization module is proposed to handle the challenge of irregular and variable defect morphologies, achieved by regularizing the deep descriptor based on the intrinsic and external correlations across various granularity attributes. Extensive experiments on three datasets with the aforementioned challenges demonstrate the superiority of the proposed methodology over other advanced approaches. © 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

Mitigating the Impact of Labeling Errors on Training via Rockafellian Relaxation

arXiv

引用

arXiv 2024年

作者： Chen, Louis L. Chern, Bobbie Eckstrand, Eric C. Royset, Amogh Mahapatra Johannes O. Department of Operations Research Naval Postgraduate School MontereyCA United States Meta Platforms Inc. United States Data Science and Analytics Group Naval Postgraduate School MontereyCA United States Department of Industrial and Systems Engineering University of Southern California United States

Labeling errors in datasets are common, arising in a variety of contexts, such as human labeling, noisy labeling, and weak labeling (i.e., image classification). Although neural networks (NNs) can tolerate modest amounts of these errors, their performance degrades substantially once error levels exceed a certain threshold. We propose a new loss reweighting, architecture-independent methodology, Rockafellian Relaxation Method (RRM) for neural network training. Experiments indicate RRM can enhance neural network methods to achieve robust performance across classification tasks in computer vision and natural language processing (sentiment analysis). We find that RRM can mitigate the effects of dataset contamination stemming from both (heavy) labeling error and/or adversarial perturbation, demonstrating effectiveness across a variety of data domains and machine learning tasks. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

OSN Rumor Control Model Based on Community Immunization

OSN Rumor Control Model Based on Community Immunization

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Ming Dong Zhiqiang Sun Zhenhua Tan Bin Zhang School of Computer Science and Engineering Northeastern University Shenyang China Software College Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry (Northeastern University) Ministry of Education China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

This paper proposes a rumor control model based on community immunization. Based on the community division and the trust network inference algorithm, the model redefines the standard to measure the importance of nodes in the network. First, the model uses the Louvain clustering algorithm based on the Ochiai coefficient to discover the network community and then presents the trust network inference algorithm. By analyzing the key factors that affect trust transfer between nodes, the trust evaluation between unfamiliar nodes is inferred, and important nodes with a high degree of trust in the network community are calculated. Finally, combined with the characteristics of inner degree and outer degree centrality of nodes in the network community, five types of important nodes in the network are screened out. To avoid repeated selection of nodes, this paper identifies a group of key nodes in the network community for local immunization by means of deduplication and taking intersection, so as to realize effective control of rumors in the network.

关键词： Distributed processing Clustering algorithms Inference algorithms Standards Open data

来源：评论

学校读者我要写书评

暂无评论

Generalization Bounds for Contextual Stochastic Optimization using Kernel Regression

arXiv

引用

arXiv 2024年

作者： Wang, Yijie Hanasusanto, Grani A. Ho, Chin Pang Graduate Program in Operations Research and Industrial Engineering The University of Texas at Austin AustinTX78712-1591 United States Department of Industrial and Enterprise Systems Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States School of Data Science City University of Hong Kong Hong Kong

In this paper, we consider contextual stochastic optimization using Nadaraya-Watson kernel regression, which is one of the most common approaches in nonparametric regression. Recent studies have explored the asymptotic convergence behavior of using Nadaraya-Watson kernel regression in contextual stochastic optimization;however, the performance guarantee under finite samples remains an open question. This paper derives a finite-sample generalization bound of the Nadaraya-Watson estimator with a spherical kernel under a generic loss function. Based on the generalization bound, we further establish a suboptimality bound for the solution of the Nadaraya-Watson approximation problem relative to the optimal solution. Finally, we derive the optimal kernel bandwidth and provide a sample complexity analysis of the Nadaraya-Watson approximation problem. © 2024, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Al_xCoCrCuFeNi (X = 0, 0.8) high entropy alloys fabricated by laser powder bed fusion

引用

Heat Treatment and Surface engineering 2024年第1期6卷

作者： Feng, Zhengjie Gao, Jingbo Zhang, Deliang School of Materials Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry (Ministry of Education) Northeastern University Shenyang China

The AlxCoCrCuFeNi (x = 0, 0.8) high entropy alloys (HEAs) were prepared by laser powder bed fusion (LPBF), and the effects of volumetric energy density (VED) and heat treatment on microstructures and mechanical proper... 详细信息

The Al_xCoCrCuFeNi (x = 0, 0.8) high entropy alloys (HEAs) were prepared by laser powder bed fusion (LPBF), and the effects of volumetric energy density (VED) and heat treatment on microstructures and mechanical properties of HEAs were investigated. The results show that the CoCrCuFeNi HEA has a single FCC phase structure and exhibits good ductility. Its yield strength is relatively low, being 520 MPa. After the alloy composition was adjusted from CoCrCuFeNi to Al_0.8CoCrCuFeNi, the HEA changed from FCC single-phase to FCC + BCC dual-phase structure and the hardness and compressive properties were significantly improved. Among them, the Al_0.8CoCrCuFeNi HEA prepared with the VED of 167 J/mm³ has the best mechanical properties, with a compressive yield strength of 652 MPa and good plasticity. After annealing at 600°C and 900°C for 1 h, the mechanical properties of HEAs are significantly improved. In particular, the microhardness and compressive yield strength of the Al_0.8CoCrCuFeNi HEA annealed at 600°C for 1 h are 378 HV and 810 MPa, respectively. The coordinated deformation between FCC and BCC domains, back stress strengthening, solid solution strengthening and precipitation strengthening after heat treatment make the Al_0.8CoCrCuFeNi HEA achieve a balance of high strength and good ductility. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： heat treatment high entropy alloys Laser powder bed fusion mechanical properties microstructures

来源：评论

学校读者我要写书评

暂无评论

Microstructure and mechanical properties of a recycled aluminum alloy fabricated by consolidation of small pieces

引用

Heat Treatment and Surface engineering 2024年第1期6卷

作者： Liu, Feifei Zhang, Deliang School of Materials Science and Engineering Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Northeastern University Shenyang China Key Laboratory of Data Analytics and Optimization for Smart Industry (Ministry of Education) Northeastern University Shenyang China

The microstructure and mechanical properties of recycled AA6063 aluminum alloy rods fabricated by hot extrusion of forging compacts formed by upsetting compacts of small AA6063 aluminum alloy pieces with different Fe contents before and after T6 heat treatment were studied. In the as-extruded state and with the higher extrusion ratio of 25:1, the microstructure consists of fully recrystallized grains, but the high iron content regions exhibit clearly finer equiaxed grains due to the stronger grain boundary pinning and nucleation effects of a higher number density of Fe-rich phase particles. Increasing the extrusion ratio increases both the strength and ductility of the as-extruded material. The reason is that increasing extrusion ratio enhances the bonding strength of the prior boundaries between the strips formed by deformation of the small pieces. In the T6 heat-treated state, increasing the extrusion ratio from 9:1 to 25:1 clearly increases the fraction of fine and equiaxed grains. The enhancement of the bonding strength and the refinement of the microstructure with the increase of extrusion ratio cause the yield strength and ultimate tensile strength to increase from 174 and 221 MPa to 213 and 237 MPa, respectively, and the elongation to fracture to decrease from 22.1 to 15.4%. Solid-state recycled samples all exhibit a ductile fracture behavior despite formation of microcracks at the prior boundaries. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Aluminum alloy hot extrusion mechanical properties microstructure solid state recycling

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Clustering and Distribution Matching with Bandit Feedback

arXiv

引用

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

DIVERSITREE: A NEW METHOD TO EFFICIENTLY COMPUTE DIVERSE SETS OF NEAR-OPTIMAL SOLUTIONS TO MIXED-INTEGER OPTIMIZATION PROBLEMS

arXiv

引用

arXiv 2022年

作者： Ahanor, Izuwa Medal, Hugh Trapp, Andrew C. Department of Industrial and Systems Engineering University of Tennessee-Knoxville United States Business School Data Science Program Worcester Polytechnic Institute United States

While most methods for solving mixed-integer optimization problems compute a single optimal solution, a diverse set of near-optimal solutions can often lead to improved outcomes. We present a new method for finding a set of diverse solutions by emphasizing diversity within the search for near-optimal solutions. Specifically, within a branch-and-bound framework, we investigated parameterized node selection rules that explicitly consider diversity. Our results indicate that our approach significantly increases the diversity of the final solution set. When compared with two existing methods, our method runs with similar runtime as regular node selection methods and gives a diversity improvement between 12% and 190%. In contrast, popular node selection rules, such as best-first search, in some instances performed worse than state-of-the-art methods by more than 35% and gave an improvement of no more than 130%. Further, we find that our method is most effective when diversity in node selection is continuously emphasized after reaching a minimal depth in the tree and when the solution set has grown sufficiently large. Our method can be easily incorporated into integer programming solvers and has the potential to significantly increase the diversity of solution sets. Copyright © 2022, The Authors. All rights reserved.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Eye tracking data analytics in virtual reality training: Application in Deepwater Horizon oil drilling operation

引用

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2021年第1期64卷 821 - 825页

作者： Ziho Kang Jiwon Jeon Saeed Salehi Industrial and Systems Engineering University of Oklahoma Norman OK Data Science and Analytics Program University of Oklahoma Norman OK Petroleum and Geological Engineering University of Oklahoma Norman OK

Virtual reality (VR) enable us to train in a safe environment using computer-generated simulations. One such simulated environment is the Deepwater Horizon operation, and VR enables us to evaluate trainees’ and operators’ situation awareness (SA) in a non-hazardous environment. One unobtrusive and viable SA evaluation method might be the use of eye movements, specifically the time-ordered visual scan paths. In this research, we investigated how SA can be associated with visual scan paths in an anomaly detection task within the oil drilling rig virtual reality simulator. The results show that the trainees having lower SA tended to create random visual scan paths whereas the trainees having higher SA tended to create concentrated and refined visual scan paths. The results show promise in developing timely intervention methods through analyzing the visual scan path characteristics of the trainees.

关键词： Eye tracking visual scanning patterns virtual reality training Deepwater Horizon operations situation awareness

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

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

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：