Search Results for author: Sambaran Bandyopadhyay

Found 14 papers, 9 papers with code

Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search

1 code implementation14 Jun 2022 Chandan K. Reddy, Lluís Màrquez, Fran Valero, Nikhil Rao, Hugo Zaragoza, Sambaran Bandyopadhyay, Arnab Biswas, Anlu Xing, Karthik Subbian

This paper introduces the "Shopping Queries Dataset", a large dataset of difficult Amazon search queries and results, publicly released with the aim of fostering research in improving the quality of search results.

Monolith to Microservices: Representing Application Software through Heterogeneous Graph Neural Network

1 code implementation1 Dec 2021 Alex Mathai, Sambaran Bandyopadhyay, Utkarsh Desai, Srikanth Tamilselvam

But the challenges associated with the separation of functional modules, slows down the migration of a monolithic code into microservices.

Representation Learning

Dynamic Structure Learning through Graph Neural Network for Forecasting Soil Moisture in Precision Agriculture

1 code implementation7 Dec 2020 Anoushka Vyas, Sambaran Bandyopadhyay

Soil moisture is an important component of precision agriculture as it directly impacts the growth and quality of vegetation.

Graph structure learning

Unsupervised Constrained Community Detection via Self-Expressive Graph Neural Network

1 code implementation28 Nov 2020 Sambaran Bandyopadhyay, Vishal Peter

Designing an unsupervised loss function to train a GNN and extract communities in an integrated manner is a fundamental challenge.

Clustering Community Detection +2

Integrating Network Embedding and Community Outlier Detection via Multiclass Graph Description

1 code implementation20 Jul 2020 Sambaran Bandyopadhyay, Saley Vishal Vivek, M. N. Murty

Real world networks often come with (community) outlier nodes, which behave differently from the regular nodes of the community.

Community Detection Graph Embedding +2

Robust Hierarchical Graph Classification with Subgraph Attention

no code implementations19 Jul 2020 Sambaran Bandyopadhyay, Manasvi Aggarwal, M. Narasimha Murty

Towards this end, we propose a graph classification algorithm called SubGattPool which jointly learns the subgraph attention and employs two different types of hierarchical attention mechanisms to find the important nodes in a hierarchy and the importance of individual hierarchies in a graph.

General Classification Graph Classification

Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization

no code implementations8 Jun 2020 Sambaran Bandyopadhyay, Manasvi Aggarwal, M. Narasimha Murty

Invent of graph neural networks has improved the state-of-the-art for both node and the entire graph representation in a vector space.

Graph Classification Representation Learning

Beyond Node Embedding: A Direct Unsupervised Edge Representation Framework for Homogeneous Networks

no code implementations11 Dec 2019 Sambaran Bandyopadhyay, Anirban Biswas, M. N. Murty, Ramasuri Narayanam

To the best of our knowledge, this is the first direct unsupervised approach for edge embedding in homogeneous information networks, without relying on the node embeddings.

Link Prediction Network Embedding

Subgraph Attention for Node Classification and Hierarchical Graph Pooling

no code implementations25 Sep 2019 Sambaran Bandyopadhyay, Manasvi Aggarwal, M. N. Murty

Along with attention over the subgraphs, our pooling architecture also uses attention to determine the important nodes within a level graph and attention to determine the important levels in the whole hierarchy.

Graph Classification Node Classification

Outlier Aware Network Embedding for Attributed Networks

3 code implementations19 Nov 2018 Sambaran Bandyopadhyay, Lokesh N, M. N. Murty

We also consider different downstream machine learning applications on networks to show the efficiency of ONE as a generic network embedding technique.

Network Embedding

FSCNMF: Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks

1 code implementation15 Apr 2018 Sambaran Bandyopadhyay, Harsh Kara, Aswin Kannan, M. N. Murty

In this work, we propose a nonnegative matrix factorization based optimization framework, namely FSCNMF which considers both the network structure and the content of the nodes while learning a lower dimensional vector representation of each node in the network.

Social and Information Networks

Cannot find the paper you are looking for? You can Submit a new open access paper.