arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2026-04-22 至 2026-04-22 共收录 3
2604.19672 2026-04-22 cs.LG stat.ML

Budgeted Online Influence Maximization

预算化的在线影响力最大化

Pierre Perrault, Jennifer Healey, Zheng Wen, Michal Valko

机构 * Adobe Research(Adobe研究院) Inria Lille(Inria里尔分校) DeepMind(深度Mind)

AI总结 本文提出一种新的预算化框架,考虑广告活动的总成本而非传统选择影响者集合的基数约束。通过独立级联扩散模型和边级半带反馈,提出算法并提供理论和实验结果,改进了基数约束下的后悔界。

Comments 37th International Conference on Machine Learning (ICML 2020), 28 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04818 2026-04-22 cs.CV eess.IV stat.ML

Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models

基于扩散模型的实时无重建异常检测与分割

Mehrdad Moradi, Marco Grasso, Bianca Maria Colosimo, Kamran Paynabar

机构 * H. Milton Stewart School of Industrial and Systems Engineering(H. Milton Stewart工业与系统工程学院) Georgia Institute of Technology(佐治亚理工学院) Department of Mechanical Engineering(机械工程系) Polytechnic University of Milan(米兰理工学院)

AI总结 本文提出RADAR方法,通过注意力机制的扩散模型直接生成异常图,提升检测精度和效率,实验证明在MVTec-AD和3D打印材料数据集上均优于现有方法。

Comments 9 pages, 8 figures, 1 table. Accepted to 2025 International Conference on Machine Learning and Applications (ICMLA)

Journal ref Proc. 2025 International Conference on Machine Learning and Applications (ICMLA), Boca Raton, FL, USA, 2025, pp. 663-670

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08404 2026-04-22 cs.LG stat.ML

Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization

对抗性标签不变图数据增强用于分布外泛化

Simon Zhang, Ryan P. DeMilt, Kun Jin, Cathy H. Xia

机构 * Department of Computer Science, Purdue University(普渡大学计算机科学系) Department of Computer Science and Engineering, The Ohio State University(俄亥俄州立大学计算机科学与工程系) Department of Industrial and Systems Engineering, The Ohio State University(俄亥俄州立大学工业与系统工程系)

AI总结 本文提出RIA方法,通过对抗性标签不变的数据增强提升分布外泛化能力,结合因果生成图数据进行优化,实验表明其在多种分布偏移场景中表现优异。

Comments 22 pages, 3 figures, accepted at ICML SCIS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏