Publications
For a complete list of my publications, please visit my Google Scholar Profile.
* indicates equal contribution
Pre-Prints
Krishnateja Killamsetty, Alexandre V. Evfimievski, Tejaswini Pedapati, Kiran Kate, Lucian Popa, Rishabh Iyer. “MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning”. arXiv:2301.13287.
Peer-Reviewed Publications (Conferences & Journals)
Nathan Beck, Krishnateja Killamsetty, Suraj Kothawade, Rishabh Iyer. Beyond Active Learning: Leveraging the Full Potential of Human Interaction via Auto-Labeling, Human Correction, and Human Verification. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.
H S V N S Kowndinya Renduchintala, Krishnateja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh K Iyer, Balaji Krishnamurthy. “INGENIOUS: Using Informative Data Subsets for Efficient Training of Large Language Models”. In Findings of Empirical Methods in Natural Language Processing, 2024.
Krishnateja Killamsetty, Guttu Sai Abhishek, Aakriti, Alexandre V. Evfimievski, Lucian Popa, Ganesh Ramakrishnan, Rishabh Iyer. “AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning”. In Neural Information Processing Systems, NeurIPS 2022. (25.6% Acceptance Rate)
Athresh Karanam*, Krishnateja Killamsetty*, Harsha Kokel*, Rishabh K Iyer. “Orient: Submodular Mutual Information Measures for Data Subset Selection under Distribution Shift”. In Neural Information Processing Systems, NeurIPS 2022. (25.6% Acceptance Rate)
Xujiang Zhao*, Killamsetty Krishnateja*, Rishabh Iyer, Feng Chen. “How Out of Distribution Data Hurts Semi-Supervised Learning”. In IEEE International Conference on Data Mining, ICDM 2022. (9% Acceptance Rate)
Rishabh Tiwari, Krishnateja Killamsetty, Rishabh Iyer, Pradeep Shenoy, “GCR: Gradient Coreset based Replay Buffer Selection for Continual Learning”. In Conference on Computer Vision and Pattern Recognition, CVPR 2022.
Ayush Maheshwari*, Krishnateja Killamsetty*, Ganesh Ramakrishnan, Rishabh Iyer, Marina Danilevsky, Lucian Popa. “Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming”. In Findings of the Association for Computational Linguistics: ACL 2022. (Long paper)
Krishnateja Killamsetty*, Changbin Li*, Chen Zhao, Rishabh Iyer, Feng Chen. “A Nested Bi-level Optimization Framework for Robust Few Shot Learning”. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022. (15% Acceptance Rate)
Krishnateja Killamsetty, Xujiang Zhou, Feng Chen, and Rishabh Iyer, “RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning”. In Neural Information Processing Systems, NeurIPS 2021. (26% Acceptance Rate)
Suraj Kothawade, Nathan Beck, Krishnateja Killamsetty, Rishabh Iyer, “SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios”. In Neural Information Processing Systems, NeurIPS 2021. (26% Acceptance Rate)
Ayush Maheshwari, Oishik Chatterjee, Krishnateja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer.“Semi-Supervised Data Programming with Subset Selection”. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 4640–4651. doi:10.18653/v1/2021.findings-acl.408. (Long paper)
Krishnateja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Abir De, Rishabh Iyer. “GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training”. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, 139:5464–5474. Proceedings of Machine Learning Research. PMLR, 2021. (21% acceptance rate)
Krishnateja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Rishabh Iyer. “GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning”. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Virtual Event, February 2-9, 2021, 8110–8118. AAAI Press, 2021. (21% Acceptance Rate)
Patents
Boddeti Mohanvarakrishna, Gautam Raju, Krishnateja Killamsetty, Swadeep Kumar, SYSTEM AND METHOD FOR ASSIGNING RESPONSIBILITY SCORES TO USERS OF VEHICLE, Indian Patent (Application No: 201911022751)
Boddeti Mohanvarakrishna, Gautam Raju, Krishnateja Killamsetty, Swadeep Kumar, SYSTEM AND METHOD FOR PREDICTING BEHAVIOUR OF A USER OF A VEHICLE, Indian Patent (Application No: 201911022492)
Boddeti Mohanvarakrishna, Gautam Raju, Krishnateja Killamsetty, Kishore Subramanian, METHOD AND SYSTEM FOR EXTRACTING AND GENERATING CRITICAL TEST SCENARIOS FOR AUTONOMOUS VEHICLES, Indian Patent (Application No: 201841048116)
Software
Krishnateja Killamsetty, Dheeraj N Bhat, Rishabh Iyer. “CORDS: COResets and Data Subset selection”. GitHub repository. GitHub, 2021.
Workshop Papers
Krishnateja Killamsetty, Alexandre Evfimievski, Tejaswani Pedapati, Kiran Kate, Lucian Popa, Rishabh K Iyer. “MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning”. The 4th workshop of Practical ML for Developing Countries Workshop(PML4DC), In Conjunction with ICLR 2023. (ORAL)
H S V N S Kowndinya Renduchintala, Krishnateja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh K Iyer, Balaji Krishnamurthy. Using Informative Data Subsets for Efficient Training of Large Language Models: An Initial Study. The 2nd workshop of Efficient Natural Language and Speech Processing (ENLSP), In Conjunction with NeurIPS 2022.
Krishnateja Killamsetty*, Changbin Li*, Chen Zhao, Rishabh Iyer, Feng Chen. “A Nested Bi-level Optimization Framework for Robust Few Shot Learning”. Fifth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems, In Conjunction with NeurIPS 2021
Savan Amitbhai Visalpara, Krishnateja Killamsetty, Rishabh Iyer. “A Data Subset Selection Framework for Efficient Hyper-Parameter Tuning and Automatic Machine Learning”. Workshop on Subset Selection in Machine Learning, SubSetML 2021, In Conjunction with ICML 2021
Krishnateja Killamsetty, Durga Sivasubramanian, Baharan Mirzasoleiman, Ganesh Ramakrishnan, Abir De, Rishabh Iyer. “A Gradient Matching Framework for Efficient Learning”. Workshop on Hardware Aware Efficient Training, In Conjunction with ICLR 2021