Birdie Blog

Thinking will not overcome fear but action will.

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

A linearithmic heuristic for the travelling salesman problem

EJOR2021 分治求解TSP

A linearithmic heuristic for the travelling salesman problem European Journal of Operational Research 2021 University of Applied Sciences of Western Switzerland 方法 RecorderPath 输入：...

Posted by Birdie on February 26, 2024

Unsupervised Learning Permutations for TSP using Gumbel-Sinkhorn Operator

NIPS23 学习置换 + 不同分布的泛化 + 理论解释

Unsupervised Learning Permutations for TSP using Gumbel-Sinkhorn Operator 基于Gumbel-Sinkhorn算子的TSP无监督学习置换 来自康奈尔大学 （这篇文章和NIPS23 Unsupervised Learning for Solving the Travelling Salesman Problem是同一...

Posted by Birdie on January 25, 2024

Unsupervised Learning for Solving the Travelling Salesman Problem

NIPS23 SAG(GNN) + 带有local search的树搜索

Unsupervised Learning for Solving the Travelling Salesman Problem 求解旅行商问题的无监督学习 来自康奈尔大学 摘要 我们提出了一种用于解决旅行商问题(TSP)的无监督学习框架UTSP。我们使用代理损失来训练图神经网络(GNN)。GNN输出一个热图，表示每条边成为最优路径一部分的概率。然后，我们应用局部搜索来生成基于热图...

Posted by Birdie on January 24, 2024

Neural Combinatorial Optimization with Heavy Decoder-Toward Large Scale Generalization

NIPS23 重解码轻编码 + 迭代重构局部解改进

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization 重解码器的神经组合优化:面向大规模泛化 来自南方科技大学和香港城市大学 开源：https://github.com/CIAM-Group/NCO_code/tree/main/single_objective/L...

Posted by Birdie on January 23, 2024

Let the Flows Tell Solving Graph Combinatorial Problems with GFlowNets

NIPS23 GFlowNets

NIPS23 Let the Flows Tell Solving Graph Combinatorial Problems with GFlowNets 用GFlowNets求解图组合优化问题 来自Mila实验室和Google DeepMind 开源：https://github.com/zdhNarsil/GFlowNet-CombOpt （没研究过相关内容，没看懂） 摘要 ...

Posted by Birdie on January 23, 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 IJCAI 隐私保护
ABOUT ME

Birdie-Go

✉️ fangzhh6@mail2.sysu.edu.cn