Birdie Blog

Thinking will not overcome fear but action will.

Deep reinforcement learning for the dynamic and uncertain vehicle routing problem

动态不确定VRP

Deep reinforcement learning for the dynamic and uncertain vehicle routing problem 2023 Applied Intelligence 福州大学经济与管理学院 摘要 对现实城市物流进行准确、实时的跟踪已成为智能交通领域的热门研究课题。而城市物流服务的路径选择通常是通过复杂的数学和分析方法来完成的。然而，现...

Posted by Birdie on August 25, 2024

TAP：Transparent and Privacy-Preserving Data Services

隐私保护 透明日志

TAP: Transparent and Privacy-Preserving Data Services 出自：32nd USENIX Security Symposium (USENIX Security 23) 摘要 如今的用户期望从处理他们数据的服务中获得更多的安全性。除了传统的数据隐私和完整性要求外，他们还期望透明度，即服务对数据的处理可以由用户和受信任的审计员进行验证。...

Posted by Birdie on June 19, 2024

Merkle2：A Low-Latency Transparency Log System

隐私保护 透明日志

Merkle2：A Low-Latency Transparency Log System 2021 IEEE Symposium on Security and Privacy (SP) Yuncong Hu, Kian Hooshmand, Harika Kalidhindi, Seung Jin Yang*, Raluca Ada Popa 加利福利亚大学，伯克利 摘要 透明...

Posted by Birdie on June 18, 2024

H-TSP Hierarchically Solving the Large-Scale Travelling Salesman Problem

AAAI2023 分治 大规模TSP

H-TSP Hierarchically Solving the Large-Scale Travelling Salesman Problem AAAI 2023 杭州电子科技大学和微软亚洲研究所 摘要 本文提出了一个基于分层强化学习的端到端学习框架，称为H-TSP，用于解决大规模旅行商问题（TSP）。该方法包含两个策略：上层策略用于将原始的规模较大的问题拆解成多个规模较小的子问题...

Posted by Birdie on June 9, 2024

Compositional Messagepassing Neural Network (CMPNN)

IJCAI2020 CMPNN

Compositional Messagepassing Neural Network (CMPNN) 选自： Communicative Representation Learning on Attributed Molecular Graphs（IJCAI20） A reinforcement learning approach for optimizing multipl...

Posted by Birdie on June 5, 2024

SplitNet A Reinforcement Learning Based Sequence Splitting Method for the MinMax Multiple Travelling Salesman Problem

AAAI2023 从TSP重构MinMax mTSP

SplitNet: A Reinforcement Learning Based Sequence Splitting Method for the MinMax Multiple Travelling Salesman Problem AAAI23 天津大学和华为诺亚方舟实验室 摘要 MinMax Multiple Travelling Salesman Problem(mTSP)...

Posted by Birdie on May 29, 2024

Looking Ahead to Avoid Being Late Solving Hard-Constrained Traveling Salesman Problem

Arxiv

Looking Ahead to Avoid Being Late: Solving Hard-Constrained Traveling Salesman Problem https://arxiv.org/abs/2403.05318v1 （我感觉整体一般） 摘要 许多现实问题都可以被表述为受限旅行商问题(TSP)。然而，约束条件总是复杂和众多的，使得求解tsp具有挑战性。当复杂...

Posted by Birdie on May 27, 2024

MVMoE Multi-Task Vehicle Routing Solver with Mixture-of-Experts

ICML2024 混合专家层

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts 代码：https://github.com/RoyalSkye/Routing-MVMoE 摘要 学习求解车辆路径问题(vrp)已经引起了人们的广泛关注。然而，大多数神经解算器仅针对特定问题进行结构化和独立训练，这使得它们不那么通用和实用。在本文中，我们...

Posted by Birdie on May 16, 2024

EFFICIENT TRAINING OF MULTI-TASK COMBINAROTIAL NEURAL SOLVER WITH MULTI-ARMED BANDITS

多臂赌博机 多任务神经组合优化求解器

EFFICIENT TRAINING OF MULTI-TASK COMBINAROTIAL NEURAL SOLVER WITH MULTI-ARMED BANDITS 使用多臂赌博机（MAB）高效训练多任务神经组合优化求解器 https://arxiv.org/abs/2305.06361 （没太仔细研究，在看MVMoE: Multi-Task Vehicle Routing ...

Posted by Birdie on May 15, 2024

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances

AAAI2021 分支热图预测 + MCTS

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances 将一个小的预训练模型推广到任意大的TSP实例 AAAI2021 代码：https://github.com/Spider-scnu/TSP （用到的 k-opt 和NIPS23有一篇很相似） 摘要 对于旅行商问题(TSP)，现有的基于监督...

Posted by Birdie on February 29, 2024

FEATURED TAGS
神经网络 机器学习 机器人 webot 通信原理 并行计算 信息安全 自然语言处理 数据库 数字图像处理 软件工程 编译原理 强化学习 数字电路 proteus 计算机组成原理 VIVADO JAVA 论文阅读 组合优化 NIPS AAAI ICML IJCAI 隐私保护 ICLR
ABOUT ME

Birdie-Go

✉️ fangzhh6@mail2.sysu.edu.cn