Rohit Babbar

Assistant professor

T313 Dept. Computer Science

I am an Assistant Professor at the department of Computer Science, Aalto University in Finland. Along with my research group, we work on problems in large scale machine learning particularly encountered in extreme classification with large output spaces, and robustness

Full researcher profile

https://research.aalto.fi/...

Areas of expertise

large scale learning, extreme multi-label classification, deep learning, sequential data, robustness

Research groups

Professorship Babbar Rohit, Assistant Professor
Computer Science Professors, Assistant Professor
Computer Science - Artificial Intelligence and Machine Learning (AIML), Assistant Professor

Publications

Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification

Sujay Khandagale, Han Xiao, Rohit Babbar 2020 Machine Learning

Why state-of-the-art deep learning barely works as good as a linear classifier in extreme multi-label text classification

Mohammadreza Mohammadnia Qaraei, Sujay Khandagale, Rohit Babbar 2020 ESANN 2020 - Proceedings, 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Rohit Babbar

Areas of expertise

Research groups

Publications

Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification

Why state-of-the-art deep learning barely works as good as a linear classifier in extreme multi-label text classification

Distributed Inference Acceleration with Adaptive DNN Partitioning and Offloading

Neural Architecture Search for Extreme Multi-label Text Classification

Unbiased Loss Functions for Extreme Classification With Missing Labels

Data scarcity, robustness and extreme multi-label classification

A Simple and Effective Scheme for Data Pre-processing in Extreme Classification

Adversarial Extreme Multi-label Classification

Prediction of glucose tolerance without an oral glucose tolerance test

Extreme Multi-label Classification for Information Retrieval

DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification

Learning Taxonomy Adaptation in Large-scale Classification

TerseSVM : A scalable approach for learning compact models in Large-scale classification

Efficient Model Selection for Regularized Classification by Exploiting Unlabeled Data

On Power Law Distributions in Large-scale Taxonomies

Re-ranking Approach to Classification in Large-scale Power-law Distributed Category Systems

Maximum-margin Framework for Training Data Synchronization in Large-scale Hierarchical Classification

On Flat versus Hierarchical Classification in Large-Scale Taxonomies

On Empirical Tradeoffs in Large Scale Hierarchical Classification

Adaptive Classifier Selection in Large-scale Hierarchical Classification

Clustering based approach to learning regular expressions over large alphabet for noisy unstructured text