Attention Solves Your TSP

By Wouter Kool, Max Welling. 2018

58 citations recorded by the source corpus.

Subfields: Model Architectures, Algorithms & Complexity

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

In Algorithms & Complexity

Citations in the corpus

Structured agents for physical construction (2019, neutral): “These models have also begun to be incorporated into model-free and model-based RL, in domains such as combinatorial optimization, motor control, and game playing (Dai et al., 2017; Kool & Welling, 2018; Wang et al., 2018; Sanchez-Gonzalez et al., 2018; Zambaldi et al., 2019).”
Relational inductive biases, deep learning, and graph networks (2018, background): “In combinatorial optimization problems, Bello et al. (2016); Nowak et al. (2017); Dai et al. (2017); Kool and Welling (2018) showed that GNs could generalize well to problems of much diﬀerent sizes than they had been trained on.”
Relational Deep Reinforcement Learning (2018, background): “This approach builds off previous work suggesting that relational computations needn’t necessarily be biased by entities’ spatial proximity [20, 10, 21, 11, 13], and may also profit from iterative structured reasoning [22, 23, 24, 25].”
Hyperbolic Attention Networks (2018, methodology): “…that 3 Attention as a building block for relational reasoning Learning relations in a graph by using neural networks to model the interactions or relations has shown promising results in visual question answering [34], modelling physical dynamics [3], and reasoning over graphs [21, 43, 16, 18].”
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search (2018, background): “ Go, which is theoretically intractable [35, 36]. Recent work has also considered classic NP-hard problems, such as Satisﬁability, Travelling Salesman, Knapsack, Minimum Vertex Cover, and Maximum Cut [39, 6, 10, 33, 26]. The appeal of learning-based approaches is that they may discover useful patter”
Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon (2018, methodology): “Indeed, all of the papers tackling TSP through ML and attempting to solve larger instances see degrading performance as size increases much beyond the sizes seen during training (Vinyals et al., 2015; Bello et al., 2017; Khalil et al., 2017a; Kool and Welling, 2018).”