Rohit Babbar
Visitor
Visitor
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
Honors and awards
Outstanding Reviewer Award ACL 2021 Conference
Award or honor granted for a specific work
Computer Science Professors
Jul 2021
Publications
CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification
Siddhant Kharbanda, Atmadeep Banerjee, Erik Schultheis, Rohit Babbar
2022
Advances in Neural Information Processing Systems 35 (NeurIPS 2022)
Adversarial examples for extreme multilabel text classification
Mohammadreza Mohammadnia Qaraei, Rohit Babbar
2022
Machine Learning
Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model
Iiro Rastas, Yann Ciarán Ryan, Iiro Tiihonen, Mohammadreza Mohammadnia Qaraei, Liina Repo, Rohit Babbar, Eetu Mäkelä, Mikko Tolonen, Filip Ginter
2022
Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change
Beyond Standard Performance Measures in Extreme Multi-label Classification
Erik Schultheis, Marek Wydmuch, Rohit Babbar, Krzysztof Dembczynski
2022
On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification
Erik Schultheis, Rohit Babbar, Marek Wydmuch, Krzysztof Dembczynski
2022
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Speeding-up one-versus-all training for extreme classification via mean-separating initialization
Erik Schultheis, Rohit Babbar
2022
Machine Learning
Detecting Sequential Genre Change in Eighteenth-Century Texts
Jinbin Zhang, Yann Ciarán Ryan, Iiro Rastas, Filip Ginter, Mikko Tolonen, Rohit Babbar
2022
Computational Humanities Research 2022
InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification
Siddhant Kharbanda, Atmadeep Banerjee, Akash Palrecha, Devaansh Gupta, Rohit Babbar
2021
Convex Surrogates for Unbiased Loss Functions in Extreme Classification With Missing Labels
Mohammadreza Mohammadnia Qaraei, Erik Schultheis, Priyanshu Gupta, Rohit Babbar
2021
The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021
Speeding-up One-vs-All Training for Extreme Classification via Smart Initialization
Erik Schultheis, Rohit Babbar
2021