Deep Learning

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: Prof. Quentin Cappart)

Chaitanya K. Joshi

Graph Neural Networks for the Travelling Salesman Problem

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? (NeurIPS 2019 Workshop)

Chaitanya K. Joshi, Thomas Laurent, Xavier Bresson

On Learning Paradigms for the Travelling Salesman Problem

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

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

Neural Combinatorial Optimization

Can Neural Networks learn to solve NP-hard optimization problems in scheduling, transportation, and supply chain directly without human handcrafting?

Chaitanya K. Joshi

Last updated on Dec 24, 2021 4 min read

Neural Combinatorial Optimization

Spatial Graph Convolutional Networks

An introduction to deep learning on graphs and geometric data with Graph Neural Networks.

Chaitanya K. Joshi

Last updated on Jun 19, 2021 4 min read

Spatial Graph Convolutional Networks

Does AI need Innate Conceptual Primitives

The legendary Rationalism versus Empiricism debate for building Artificially Intelligent systems.

Chaitanya K. Joshi

Apr 23, 2019 10 min read

Does AI need Innate Conceptual Primitives

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

Graph Convolutional Neural Networks for the Travelling Salesman Problem

Utilizing Embeddings for Efficient Matching of Entities

Learning low-dimensional vector spaces of financial statements and invoices for constructing semantic similarity graphs. (US Patent)

Sean Saito, Chaitanya K. Joshi, Raja Shanmugamani, Truc Viet Le, Rajesh Vellore Arumugam

Utilizing Embeddings for Efficient Matching of Entities

Graphical Approach to Multi-Matching

Matching financial statements and invoices via graph combinatorial optimization algorithms on semantic similarity graphs. (US Patent)

Truc Viet Le, Sean Saito, Chaitanya K. Joshi, Raja Shanmugamani

Graphical Approach to Multi-Matching

Representing Sets of Entites for Matching Problems

Representing sets of financial statements and invoices as bags-of-features. (US Patent)

Sean Saito, Truc Viet Le, Chaitanya K. Joshi, Raja Shanmugamani

Representing Sets of Entites for Matching Problems