Publications

Latest publication list can be found on my Google Scholar profile.

On the Expressive Power of Geometric Graph Neural Networks

We propose a Geometric Weisfeiler-Leman test to study the expressive power of Geometric Graph Neural Networks and demonstrate the advantages of equivariant GNNs over invariant GNNs. (To appear in ICML 2023, and presented as an Oral at NeurIPS 2022 Workshop)

Chaitanya K. Joshi, Cristian Bodnar, Simon V. Mathis, Taco Cohen, Pietro Liò

On the Expressive Power of Geometric Graph Neural Networks

Multi-State RNA Design with Geometric Multi-Graph Neural Networks

We propose gRNAde, a geometric deep learning pipeline for 3D RNA inverse design conditioned on multiple backbone conformations.

Chaitanya K. Joshi, Arian R. Jamasb, Ramon Viñas, Charles Harris, Simon Mathis, Pietro Liò

Multi-State RNA Design with Geometric Multi-Graph Neural Networks

On Representation Knowledge Distillation for Graph Neural Networks

Strategies for distilling representational knowledge from expressive yet cumbersome-to-deploy GNNs to resource-efficient and lightweight architectures. (IEEE TNNLS)

Chaitanya K. Joshi, Fayao Liu, Xu Xun, Jie Lin, Chuan-Sheng Foo

On Representation Knowledge Distillation for Graph Neural Networks

Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds

We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds to learn local and global shape features. (3DV 2022)

Fayao Liu, Guosheng Lin, Chuan-Sheng Foo, Chaitanya K. Joshi, Jie Lin

Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds

Hypergraph Factorisation for Multi-tissue Gene Expression Imputation

HYFA (Hypergraph Factorisation) jointly imputates multi-tissue and cell-type gene expression via a specialised graph neural network operating on a hypergraph of individuals, metagenes, and tissues. (To appear in Nature Machine Intelligence)

Ramon Viñas, Chaitanya K. Joshi, Dobrik Georgiev, Phillip Lin, Bianca Dumitrascu, Eric R. Gamazon, Pietro Liò

Hypergraph Factorisation for Multi-tissue Gene Expression Imputation

Learning the Travelling Salesperson Problem 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

Learning the Travelling Salesperson Problem Requires Rethinking Generalization

Learning TSP Requires Rethinking Generalization

Chaitanya K. Joshi, Quentin Cappart, Louis-Martin Rousseau, Thomas Laurent

Multi-Graph Transformer for Free-Hand Sketch Recognition

Representation learning for free-hand drawings using GNNs and Transformers. (IEEE TNNLS)

Peng Xu, Chaitanya K. Joshi, Xavier Bresson

Multi-Graph Transformer for Free-Hand Sketch Recognition

Benchmarking Graph Neural Networks

Open-source benchmarking framework to identify scalable and powerful GNN architectures, and track the progress of graph representation learning research. (500+ citations, 2000+ GitHub stars)

Vijay Prakash Dwivedi, Chaitanya K. Joshi, Luu Anh Tuan, Thomas Laurent, Yoshua Bengio, Xavier Bresson

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

Working Women and Caste in India: A Study of Social Disadvantage using Feature Attribution

Feature attribution to interpret decision tree models and study the generational impact of caste on women’s work force participation in India. (ICLR 2019 Workshop)

Kuhu Joshi, Chaitanya K. Joshi

Working Women and Caste in India: A Study of Social Disadvantage using Feature Attribution

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

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

Question-answering and Chatbots using Memory Networks

We discuss the Question-Answering task in NLP, and introduce a class of deep learning models known as memory networks to build QA and chatbot systems.

Chaitanya K. Joshi

Question-answering and Chatbots using Memory Networks

Personalization in Goal-oriented Dialog

New datasets and Memory Network architectures for studying personalized dialog systems based on user profiles. (NeurIPS 2017 Workshop)

Chaitanya K. Joshi, Fei Mi, Boi Faltings