Hello, I am an Assistant Professor in the department of Computer Science, Aalto University at Helsinki, Finland. In my team, we work on large-scale machine learning problems particularly in Extreme Classification and learning with imperfect supervision.
Before this, I was a post-doc at Max-Planck Institute for Intelligent Systems, Tuebingen, Germany in the group of Prof. Bernhard Schölkopf. I finished my PhD from University of Grenoble, France where I was advised by Prof. Eric Gaussier and Prof. Massih-Reza Amini
NEWS
June 2022 : Academy of Finland grant (370K euros) - Scalable and Robust Representation Learning in Large Output Spaces has been accepted. Looking for motivated PhD students and Research Assistants with experience/strong willingness to develop theoretically sound frameworks and deep learning algorithms (Transformer encoders) for large output spaces and missing/noisy labels. Email me at firstname.lastname@aalto.fi, if you are interested.
Dec 2021 : Our Academy of Finland grant (205K euros) for Discourse Detection in Large-scale Textual Corpora has been accepted. Looking for motivated PhD students or Post-docs with experience/strong willingness to learn and develop NLP techniques with deep learning for analysis of noisy text corpora. Email me at firstname.lastname@aalto.fi, if you are interested.
Recent pre-prints
Unbiased Loss Functions for Multilabel Classification with Missing Labels, 2021, (arXiv pre-print)
Erik Schultheis, Rohit BabbarEmbedding Convolutions for Short Text Extreme Classification with Millions of Labels, 2021, (arXiv pre-print)
Siddhant Kharbanda, Atmadeep Banerjee, Akash Palrecha, Rohit BabbarAdversarial Examples for Extreme Multi-label Classification, 2021, (arxiv-preprint)
Mohamaadreza Qaraei, Rohit Babbar
Selected Publications (All publications on google scholar)
CascadeXML : End-to-end Multi-Resolution Learning for Extreme Multi-Label Text Classification,
Siddhant Kharbanda, Atmadeep Banerjee, Erik Schultheis and Rohit Babbar
36th Conference on Neural Information Processing Systems, NeurIPS, 2022On Missing Labels, Long tails and propensities in Extreme Multi-label Classification,
Erik Schultheis, Marek Wydmuch, Rohit Babbar, and Krzysztof Dembczyński
28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022Speeding-up One-vs-All Training for Extreme Classification via Mean-separating Initialization, (arxiv pre-print, Code)
Erik Schultheis, and Rohit Babbar
ECML & Machine Learning Journal Track, ECML-MLJ, 2022Convex Surrogates for Unbiased Loss Functions in Extreme Classification With Missing Labels (pdf, video, code)
Mohammadreza Qaraei, Erik Schultheis, Priyanshu Gupta, Rohit Babbar
30th ACM International World Wide Web Conference, The WebConf (WWW) 2021Propensity-scored Probabilistic Label Trees pdf
Marek Wydmuch, Kalina Jasinska-Kobus, Rohit Babbar and Krzysztof Dembczyński
44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2021)
Distributed Inference Acceleration with Adaptive DNN Partitioning and Offloading pdf
Mohammed Thaha, Carlee Joe-Wong, Rohit Babbar, Mario Di Francesco
20th IEEE International Conference on Computer Communications, Infocom 2020
Bonsai - Diverse and Shallow Trees for Extreme Multi-label Classification pdf
Code Rust implementation by Tom Dong Datasets
Sujay Khandagale, Han Xiao, Rohit Babbar
Machine Learning Journal 2020
Data Scarcity, Robustness and Extreme Multi-label Classification pdf Code, Datasets
Rohit Babbar and Bernhard Schölkopf
Machine Learning Journal and European Conference on Machine Learning (ECML) 2019
DiSMEC : Distributed Sparse Machines for Extreme Multi-label Classification, pdf Code Dataset
Rohit Babbar and Bernhard Schölkopf
ACM International Conference on Web Search and Data Mining (WSDM) 2017, Cambridge
Learning Taxonomy Adaptation in Large-scale Classification
Rohit Babbar, Ioannis Partalas, Eric Gaussier and Massih-reza Amini
Journal of Machine Learning Research , (JMLR 2016)
Teaching
Kernel Methods in Machine Learning (5 ECTS, Spring 2019, 2020, 2021)
Introduction to Data Science (Bachelor level, 5 ECTS, Fall 2019)
Supervised Learning with Large Label Sets ( 3 ECTS, Spring 2018)
Reviewing activities :
2019 - AAAI, ICLR, AISTATS, ICML, NIPS, IJCAI, JMLR, MLJ
2018 - NIPS, ICML, ICLR, AISTATS, AAAI, JMLR, IEEE PAMI
2017 - NIPS, ICML, ICLR, AISTATS
Academic Trail :
Researcher at the Empirical Inference group headed by Prof. Bernhard Schölkopf (2015 - 2017), at Max-Planck Institute for Intelligent Systems, Tübingen, Germany
Doctoral Degree in Computer Science from University of Grenoble Alpes, (2011-2014) advised by Prof. Eric Gaussier and Prof. Massih-Reza Amini.
Master in Computer Science, 2009-2011, from Chennai Mathematical Institute, India. Did my master thesis (Jan-June, 2011) under supervision of Dr. Manik Varma and Prof. Madhavan Mukund
Other Stuff
- Long ago, finished Grenoble-Vizille Semi-marathon