Chaitanya K. Joshi
Chaitanya K. Joshi
Home
Publications
Projects
Blog
Talks
CV
Light
Dark
Automatic
Combinatorial Optimization
Learning TSP Requires Rethinking Generalization
We study zero-shot generalization to large-scale instances in neural network-driven solvers for the Travelling Salesman Problem: what architectures, inductive biases and learning paradigms enable better generalization?
(Invited submission to the Constraints Journal)
Chaitanya K. Joshi
,
Quentin Cappart
,
Louis-Martin Rousseau
,
Thomas Laurent
PDF
Cite
Code
Project
Slides
Video
DOI
Learning TSP Requires Rethinking Generalization
This talk discusses our recent work on deep learning for TSP and the challenge of zero-shot generalization for large-scale and real-world routing problems.
Jun 8, 2021 12:00 AM
CORS 2021 (Host: Maxime Gasse)
Chaitanya K. Joshi
Project
Slides
Video
Benchmarking Graph Neural Networks
Open-source benchmarking framework to identify scalable and powerful GNN architectures, and track the progress of graph representation learning research.
(1500+ GitHub Stars)
Vijay Prakash Dwivedi
,
Chaitanya K. Joshi
,
Thomas Laurent
,
Yoshua Bengio
,
Xavier Bresson
PDF
Cite
Code
Project
Slides
Press
Graph Neural Networks for the Travelling Salesman Problem
This talk introduces a recent line of work using Graph Neural Networks to directly ‘learn’ good heuristics for TSP in an end-to-end manner.
Oct 22, 2019 12:00 AM
INFORMS Annual Meeting 2019 (Host: Quentin Cappart)
Chaitanya K. Joshi
Project
Slides
On Learning Paradigms for the Travelling Salesman Problem
How do learning paradigms impact zero-shot generalization to large-scale instances in learning-driven TSP solvers?
Chaitanya K. Joshi
,
Thomas Laurent
,
Xavier Bresson
PDF
Cite
Code
Project
Poster
An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
Deep Graph ConvNets paired with parallelized graph search can learn TSP up to few hundred cities, but fall short of classical solvers.
Chaitanya K. Joshi
,
Thomas Laurent
,
Xavier Bresson
PDF
Cite
Code
Project
Project
Slides
Combinatorial Optimization
Neural Networks for learning to solve combinatorial optimization problems.
Chaitanya K. Joshi
Neural Combinatorial Optimization
Can Neural Networks learn to solve NP-hard optimization problems in scheduling, transportation, and supply chain directly from data?
Chaitanya K. Joshi
Last updated on Jun 20, 2021
4 min read
Project
Graph Convolutional Neural Networks for the Travelling Salesman Problem
Combinatorial optimization problems, also called NP-hard problems, are practical constraint satisfaction problems that are impossible …
Chaitanya K. Joshi
PDF
Cite
Code
Project
Poster
Slides
Video
DOI
Utilizing Embeddings for Efficient Matching of Entities
Learning low-dimensional vector spaces of financial statements and invoices for constructing semantic similarity graphs.
Sean Saito
,
Chaitanya K. Joshi
,
Raja Shanmugamani
,
Truc Viet Le
,
Rajesh Vellore Arumugam
PDF
Cite
Project
»
Cite
×