Publications

For the complete list, please see my Google Scholar Profile.
* indicates equal contribution

2023

Data-Efficient Contrastive Self-supervised Learning: Easy Examples Contribute the Most
Siddharth Joshi, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2023
[pdf] [Project page]
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning
Yu Yang, Besmira Nushi, Hamid Palangi, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2023
[pdf]
Which Features are Learned by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
Yihao Xue, Siddharth Joshi, Eric Gan, Pin-Yu Chen, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2023 (Long presentation)
[pdf] [long]
Towards Sustainable Learning: Coresets for Data-efficient Deep Learning
Yu Yang, Kang Hao, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2023
High Probability Bounds for Stochastic Continuous Submodular Maximization
Evan Becker, Jingdong Gao, Ted Zadouri, Baharan Mirzasoleiman
Proc. Artificial Intelligence and Statistics (AISTATS), 2023
[pdf] [long]
Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks
Wenhan Yang, Baharan Mirzasoleiman
ArXiv, 2023
[pdf]
Graph Contrastive Learning under Heterophily
Wenhan Yang, Baharan Mirzasoleiman
ArXiv, 2023
[pdf]
A Self-supervised Framework for Improved Data-Driven Monitoring of Stress via Multi-modal Passive Sensing
Shayan Fazeli, Lionel Levine, Mehrab Beikzadeh, Baharan Mirzasoleiman, Bita Zadeh, Tara Peris, Majid Sarrafzadeh
IEEE Conference on Digital Health (ICDH), 2023
[pdf]

2022

The Final Ascent: When Bigger Models Generalize Worse on Noisy-labeled Data
Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
ArXiv preprint, 2022
[pdf]
Passive Monitoring of Physiological Precursors of Stress Leveraging Smartwatch Data
Shayan Fazeli, Lionel Levine, Mehrab Beikzadeh, Baharan Mirzasoleiman, Bita Zadeh, Tara Peris, Majid Sarrafzadeh
IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2022
[pdf]
Generating High Fidelity Synthetic Data via Coreset selection and Entropic Regularization
Omead Pooladzandi, Erik Nijkamp, Pasha Khosravi, Baharan Mirzasoleiman
NeurIPS Workshop SyntheticData4ML, 2022
[pdf]
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
Tian Yu Liu, Yu Yang, Baharan Mirzasoleiman
Proc. Advances in Neural Information Processing Systems (NeurIPS), 2022
[pdf] [long]
Data-Efficient Augmentation for Training Neural Networks
Tian Yu Liu, Baharan Mirzasoleiman
Proc. Advances in Neural Information Processing Systems (NeurIPS), 2022
[pdf] [long]
Not All Poisons are Created Equal: Robust Training against Data Poisoning
Yu Yang, Tian Yu Liu, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2022 (Long presentation)
[pdf] [long]
Investigating Why Contrastive Learning Benefits Robustness Against Label Noise
Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2022
[pdf] [long]
Adaptive Second Order Coresets for Data-efficient Machine Learning
Omead Pooladzandi, David Davini, Baharan Mirzasoleiman
Proc. International Conference on Machine Learning (ICML), 2022
[pdf] [long]
Towards Balanced Information Propagation in Social Media
Mahmoudreza Babaei, Baharan Mirzasoleiman, Jungseock Joo, Adrian Weller
ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO), 2022
[pdf]
Purification of single-cell transcriptomics data with coreset selection
Robert Palovics, Tony Wyss-Coray, Baharan Mirzasoleiman
ICML Workshop on Computational Biology, 2022
[pdf]
Low Rank Pruning via Output Perturbation
Yuhan Liu*, Siddharth Joshi*, Baharan Mirzasoleiman
Sparsity in Neural Networks Workshop (SNN), 2022
[pdf]
Analytical Models for Motifs in Temporal Networks: Discovering Trends and Anomalies
Alexander Porter, Baharan Mirzasoleiman, Jure Leskovec
International Workshop on Temporal Web Analytics (TempWeb), 2022
[pdf]

2021

On the fairness of time-critical influence maximization in social networks
Junaid Ali, Mahmoudreza Babaei, Abhijnan Chakraborty, Baharan Mirzasoleiman, Krishna P Gummadi, Adish Singla
Transactions on Knowledge and Data Engineering (TKDE), 2021
[pdf]
CrossWalk: Fairness-enhanced Node Representation Learning
Ahmad Khajehnejad, Moein Khajehnejad, Mahmoudreza Babaei, Krishna P Gummadi, Adrian Weller, Baharan Mirzasoleiman
Proc. AAAI Conference on Artificial Intelligence (AAAI), 2021
[pdf] [long]

2020

Coresets for Robust Training of Neural Networks against Noisy Labels
Baharan Mirzasoleiman, Kaidi Cao, Jure Leskovec
Proc. Advances in Neural Information Processing Systems (NeurIPS), 2020
[pdf] [long]
Coresets for Data-efficient Training of Machine Learning Models
Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec
Proc. International Conference on Machine Learning (ICML), 2020
[pdf] [long] [Code]
Coresets for Graph Based Semi-supervised Learning: Convex and Greedy Optimization
Saeed Vahidian, Baharan Mirzasoleiman, Alex Cloninger
Conference on Uncertainty in Artificial Intelligence (UAI), 2020
[pdf] [long]
Select via Proxy: Efficient Data Selection for Deep Learning
Cody Coleman, Christopher Yeh, Steve Mussmann, Baharan Mirzasoleiman, Peter Bailis, Percy Liang, Jure Leskovec, Matei Zaharia
Proc. International Conference on Learning Representations (ICLR), 2020
[pdf] [long]

2019

On the Fairness of Time-Critical Influence Maximization in Social Networks
Junaid Ali, Mahmoudreza Babaei, Abhijnan Chakraborty, Baharan Mirzasoleiman, Krishna Gummadi, Adish Singla
Proc. NeurIPS Workshop on Human-Centric Machine Learning, 2019
[ArXiv]

2018

Dynamic Network Model from Partial Observations
Elahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec
Proc. Advances in Neural Information Processing Systems (NeurIPS), 2018
[pdf]
Streaming Non-monotone Submodular Maximization: Video Summarization on the Fly
Baharan Mirzasoleiman, Stefanie Jegelka, Andreas Krause
Proc. Conference on Artificial Intelligence (AAAI), 2018
[pdf], [long]

2017

Big Data Summarization Using Submodular Functions
Baharan Mirzasoleiman
Ph.D. Thesis, ETH Zurich, 2017
[pdf]
Deletion Robust Submodular Maximization: Data Summarization with the right to be forgotten
Baharan Mirzasoleiman, Amin Karbasi, Andreas Krause
Proc. International Conference on Machine Learning (ICML), 2017
[pdf], [long]
Guaranteed Non-Convex Optimization: Submodular Maximization over Continuous Domain
Yatao (An) Bian, Baharan Mirzasoleiman, Joachim Buhmann, Andreas Krause
Proc. International Conference on Artificial Intelligence and Statistics (AISTAT), 2017
[pdf], [long]

2016

Distributed Submodular Maximization
Baharan Mirzasoleiman, Amin Karbasi, Andreas Krause
Journal of Machine Learning Research (JMLR) vol. 17(238):1-44, 2016
[pdf]
Fast Distributed Submodular Cover: Public Private Data Summarization
Baharan Mirzasoleiman, Morteza Zadimoghaddam, Amin Karbasi
Proc. Advances in Neural Information Processing Systems (NIPS), 2016
[pdf], [long]
Fast Constrained Submodular Maximization: Personalized Data Summarization
Baharan Mirzasoleiman, Ashwinkumar Badanidiyuru, Amin Karbasi
Proc. International Conference on Machine Learning (ICML), 2016
[pdf], [long]
Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization
Eric Balkanski*, Andreas Krause*, Baharan Mirzasoleiman*, Yaron Singer*
Proc. International Conference on Machine Learning (ICML), 2016
[pdf], [long]

2015

Distributed Submodular Cover: Succinctly Summarizing Massive Data
Baharan Mirzasoleiman, Amin Karbasi, Ashwinkumar Badanidiyuru, Andreas Krause
Proc. Advances in Neural Information Processing Systems (NIPS), 2015
[pdf], [long]
Lazier than Lazy Greedy
Baharan Mirzasoleiman, Amin Karbasi, Ashwinkumar Badanidiyuru, Jan Vondrak, Andreas Krause
Proc. Conference on Artificial Intelligence (AAAI), 2015
[pdf]

2014

Streaming Submodular Maximization: Massive Data Summarization on the Fly
Ashwinkumar Badanidiyuru, Baharan Mirzasoleiman, Amin Karbasi, Andreas Krause
Proc. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2014
[pdf]
Modeling the Impact of User Awareness on Immunization Strategies
Baharan Mirzasoleiman, Hamid Reza Rabiee, Mostafa Salehi
Proc IEEE INFOCOM International Workshop on Network Science for Communication Networks (NetSciCom), 2014
[pdf]

2013

Distributed Submodular Maximization: Identifying Representative Elements in Massive Data
Baharan Mirzasoleiman, Amin Karbasi, Rik Sarkar, Andreas Krause
Proc. Advances in Neural Information Processing Systems (NIPS), 2013
[pdf], [long]

2012

Revenue Maximization in Social Networks through Discounting
Mahmoudreza Babaei, Baharan Mirzasoleiman, Mahdi Jalili, Mohammad Ali Safari
Social Network Analysis and Mining (SNAM) vol. 3(4): 1249-1262, Springer, 2012
[pdf]
Immunizing Complex Networks with Limited Budget
Baharan Mirzasoleiman, Mahmoudreza Babaei, Mahdi Jalili
Europhysics Letters (EPL) vol. 98(3):38004, 2012
[pdf]

2011

Cascaded Failures in Weighted Networks
Baharan Mirzasoleiman, Mahmoudreza Babaei, Mahdi Jalili, Mohammad Ali Safari
Physical Review E vol. 84(4):046114, 2011
[pdf]
Failure Tolerance of Motif Structure in Biological Networks
Baharan Mirzasoleiman, Mahdi Jalili
PLoS One vol. 6(5): e20512, 2011
[pdf]
Reuse-Attack Mitigation in Wireless Sensor Networks
Hossein Shafiei, Ahmad Khonsari, Baharan Mirzasoleiman, Mohammad Ould-Khaoua
Proc. IEEE International Conference on Communications (ICC), 2011
[pdf]

2009

Utility Proportional Optimization Flow Control for Overlay Multicast
Ali Jafari, Hossein Shafiei, Baharan Mirzasoleiman, Ghodrat Sepidnam
Proc. IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA), 2009
[pdf]