English
Related papers

Related papers: Graph Neural Networks are Heuristics

200 papers

Combinatorial optimization problems like the Traveling Salesman Problem are critical in industry yet NP-hard. Neural Combinatorial Optimization has shown promise, but its reliance on online reinforcement learning (RL) hampers deployment and…

Machine Learning · Computer Science 2026-03-27 Hironori Ohigashi , Shinichiro Hamada

Combinatorial optimization is widely applied in a number of areas nowadays. Unfortunately, many combinatorial optimization problems are NP-hard which usually means that they are unsolvable in practice. However, it is often unnecessary to…

Data Structures and Algorithms · Computer Science 2012-07-10 Daniel Karapetyan

Most reinforcement learning approaches used in behavior generation utilize vectorial information as input. However, this requires the network to have a pre-defined input-size -- in semantic environments this means assuming the maximum…

Machine Learning · Computer Science 2020-06-24 Patrick Hart , Alois Knoll

The Travelling Salesman Problem (TSP) is a challenging graph task in combinatorial optimization that requires reasoning about both local node neighborhoods and global graph structure. In this paper, we propose to use the novel Graph…

Artificial Intelligence · Computer Science 2020-07-10 Amal Nammouchi , Hakim Ghazzai , Yehia Massoud

Path-planning algorithms are an important part of a wide variety of robotic applications, such as mobile robot navigation and robot arm manipulation. However, in large search spaces in which local traps may exist, it remains challenging to…

Machine Learning · Computer Science 2019-08-12 Yuka Ariki , Takuya Narihira

Automated driving in urban scenarios requires efficient planning algorithms able to handle complex situations in real-time. A popular approach is to use graph-based planning methods in order to obtain a rough trajectory which is…

Robotics · Computer Science 2021-02-17 Oliver Speidel , Jona Ruof , Klaus Dietmayer

We introduce Limited Rollout Beam Search (LRBS), a beam search strategy for deep reinforcement learning (DRL) based combinatorial optimization improvement heuristics. Utilizing pre-trained models on the Euclidean Traveling Salesperson…

Machine Learning · Computer Science 2024-12-16 Federico Julian Camerota Verdù , Lorenzo Castelli , Luca Bortolussi

In recent years, there has been a growing interest in using learning-based approaches for solving combinatorial problems, either in an end-to-end manner or in conjunction with traditional optimization algorithms. In both scenarios, the…

Machine Learning · Computer Science 2024-03-14 Léo Boisvert , Hélène Verhaeghe , Quentin Cappart

We propose a Reinforcement Learning based approach to approximately solve the Tree Decomposition (TD) problem. TD is a combinatorial problem, which is central to the analysis of graph minor structure and computational complexity, as well as…

Machine Learning · Computer Science 2020-12-08 Taras Khakhulin , Roman Schutski , Ivan Oseledets

Neural Combinatorial Optimization aims to learn to solve a class of combinatorial problems through data-driven methods and notably through employing neural networks by learning the underlying distribution of problem instances. While, so far…

Machine Learning · Computer Science 2025-08-05 Daniela Thyssens , Tim Dernedde , Wilson Sentanoe , Lars Schmidt-Thieme

We train a small message-passing graph neural network to predict Hamiltonian cycles on Erd\H{o}s-R\'enyi random graphs in a critical regime. It outperforms existing hand-crafted heuristics after about 2.5 hours of training on a single GPU.…

Machine Learning · Computer Science 2023-06-13 Filip Bosnić , Mile Šikić

Neural Module Network (NMN) is a machine learning model for solving the visual question answering tasks. NMN uses programs to encode modules' structures, and its modularized architecture enables it to solve logical problems more reasonably.…

Artificial Intelligence · Computer Science 2020-11-30 Yuxuan Wu , Hideki Nakayama

Current methods for end-to-end constructive neural combinatorial optimization usually train a policy using behavior cloning from expert solutions or policy gradient methods from reinforcement learning. While behavior cloning is…

Machine Learning · Computer Science 2024-11-05 Jonathan Pirnay , Dominik G. Grimm

Recent advances in neural algorithmic reasoning with graph neural networks (GNNs) are propped up by the notion of algorithmic alignment. Broadly, a neural network will be better at learning to execute a reasoning task (in terms of sample…

Machine Learning · Computer Science 2022-10-12 Andrew Dudzik , Petar Veličković

Neural routing solvers (NRSs) that leverage deep learning to tackle vehicle routing problems have demonstrated notable potential for practical applications. By learning implicit heuristic rules from data, NRSs replace the handcrafted…

Optimization and Control · Mathematics 2026-03-17 Yunpeng Ba , Xi Lin , Changliang Zhou , Ruihao Zheng , Zhenkun Wang , Xinyan Liang , Zhichao Lu , Jianyong Sun , Yuhua Qian , Qingfu Zhang

Graph structure learning is a well-established problem that aims at optimizing graph structures adaptive to specific graph datasets to help message passing neural networks (i.e., GNNs) to yield effective and robust node embeddings. However,…

Machine Learning · Computer Science 2023-06-21 Wentao Zhao , Qitian Wu , Chenxiao Yang , Junchi Yan

We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and interpretability; however, learning them requires…

Machine Learning · Computer Science 2021-03-30 Ameesh Shah , Eric Zhan , Jennifer J. Sun , Abhinav Verma , Yisong Yue , Swarat Chaudhuri

Graphs can be used to represent and reason about systems and a variety of metrics have been devised to quantify their global characteristics. However, little is currently known about how to construct a graph or improve an existing one given…

Machine Learning · Computer Science 2021-10-28 Victor-Alexandru Darvariu , Stephen Hailes , Mirco Musolesi

In this work, a novel idea is presented for combinatorial optimization problems, a hybrid network, which results in a superior outcome. We applied this method to graph pointer networks [1], expanding its capabilities to a higher level. We…

Graph search planning algorithms for navigation typically rely heavily on heuristics to efficiently plan paths. As a result, while such approaches require no training phase and can directly plan long horizon paths, they often require…

Robotics · Computer Science 2025-07-29 Rishi Veerapaneni , Muhammad Suhail Saleem , Maxim Likhachev