Mohammad Mahdi Khalili

63 papers A* 7A 4C 1Journal 39Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Individual Fairness In Strategic Classification. CoRR Zhiqun Zuo, Mohammad Mahdi Khalili
2026	J	`jnl`	tensorFM: Low-Rank Approximations of Cross-Order Feature Interactions. CoRR Alessio Mazzetto, Mohammad Mahdi Khalili, Laura Fee Nern, Michael Viderman, Alex Shtoff, Krzysztof Dembczynski
2025	J	`jnl`	AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features. CoRR Xudong Zhu, Mohammad Mahdi Khalili, Zhihui Zhu
2025	J	`jnl`	An Efficient Training Algorithm for Models with Block-wise Sparsity. CoRR Ding Zhu, Zhiqun Zuo, Mohammad Mahdi Khalili
2025	J	`jnl`	An Efficient Training Algorithm for Models with Block-wise Sparsity. Trans. Mach. Learn. Res. Ding Zhu, Zhiqun Zuo, Mohammad Mahdi Khalili
2025	J	`jnl`	Demographic-Agnostic Fairness without Harm. CoRR Zhongteng Cai, Mohammad Mahdi Khalili, Xueru Zhang
2025	J	`jnl`	From Emergence to Control: Probing and Modulating Self-Reflection in Language Models. CoRR Xudong Zhu, Jiachen Jiang, Mohammad Mahdi Khalili, Zhihui Zhu
2025	—	`conf`	Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification. NAACL (Findings) Vishnu Kabir Chhabra, Ding Zhu, Mohammad Mahdi Khalili
2025	J	`jnl`	Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification. CoRR Vishnu Kabir Chhabra, Ding Zhu, Mohammad Mahdi Khalili
2025	J	`jnl`	On the transferability of Sparse Autoencoders for interpreting compressed models. CoRR Suchit Gupte, Vishnu Kabir Chhabra, Mohammad Mahdi Khalili
2025	A	`conf`	Post-processing for Fair Regression via Explainable SVD. AISTATS Zhiqun Zuo, Ding Zhu, Mohammad Mahdi Khalili
2025	J	`jnl`	Post-processing for Fair Regression via Explainable SVD. CoRR Zhiqun Zuo, Ding Zhu, Mohammad Mahdi Khalili
2025	J	`jnl`	Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability. CoRR Vishnu Kabir Chhabra, Mohammad Mahdi Khalili
2024	J	`jnl`	ECG Signal Denoising Using Multi-scale Patch Embedding and Transformers. CoRR Ding Zhu, Vishnu Kabir Chhabra, Mohammad Mahdi Khalili
2024	J	`jnl`	Federated Learning with Reduced Information Leakage and Computation. Trans. Mach. Learn. Res. Tongxin Yin, Xuwei Tan, Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2024	A	`conf`	Imposing Fairness Constraints in Synthetic Data Generation. AISTATS Mahed Abroshan, Andrew Elliott, Mohammad Mahdi Khalili
2024	J	`jnl`	Learning under Imitative Strategic Behavior with Unforeseeable Outcomes. CoRR Tian Xie, Zhiqun Zuo, Mohammad Mahdi Khalili, Xueru Zhang
2024	J	`jnl`	Learning under Imitative Strategic Behavior with Unforeseeable Outcomes. Trans. Mach. Learn. Res. Tian Xie, Zhiqun Zuo, Mohammad Mahdi Khalili, Xueru Zhang
2024	J	`jnl`	Lookahead Counterfactual Fairness. CoRR Zhiqun Zuo, Tian Xie, Xuwei Tan, Xueru Zhang, Mohammad Mahdi Khalili
2024	J	`jnl`	Lookahead Counterfactual Fairness. Trans. Mach. Learn. Res. Zhiqun Zuo, Tian Xie, Xuwei Tan, Xueru Zhang, Mohammad Mahdi Khalili
2024	A	`conf`	Privacy-Aware Randomized Quantization via Linear Programming. UAI Zhongteng Cai, Xueru Zhang, Mohammad Mahdi Khalili
2024	J	`jnl`	Privacy-Aware Randomized Quantization via Linear Programming. CoRR Zhongteng Cai, Xueru Zhang, Mohammad Mahdi Khalili
2023	J	`jnl`	Counterfactually Fair Representation. CoRR Zhiqun Zuo, Mohammad Mahdi Khalili, Xueru Zhang
2023	J	`jnl`	Differentially Private Real-Time Release of Sequential Data. ACM Trans. Priv. Secur. Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2023	J	`jnl`	Federated Learning with Reduced Information Leakage and Computation. CoRR Tongxin Yin, Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2023	A*	`conf`	Loss Balancing for Fair Supervised Learning. ICML Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan
2023	J	`jnl`	Loss Balancing for Fair Supervised Learning. CoRR Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan
2023	A*	`conf`	Symbolic Metamodels for Interpreting Black-Boxes Using Primitive Functions. AAAI Mahed Abroshan, Saumitra Mishra, Mohammad Mahdi Khalili
2023	J	`jnl`	Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functions. CoRR Mahed Abroshan, Saumitra Mishra, Mohammad Mahdi Khalili
2022	A	`conf`	An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift. AISTATS Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili, Laura Toni, Miguel R. D. Rodrigues
2022	J	`jnl`	An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift. CoRR Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili, Laura Toni, Miguel R. D. Rodrigues
2022	A*	`conf`	Fairness Interventions as (Dis)Incentives for Strategic Manipulation. ICML Xueru Zhang, Mohammad Mahdi Khalili, Kun Jin, Parinaz Naghizadeh, Mingyan Liu
2022	A*	`conf`	Incentive Mechanisms for Strategic Classification and Regression Problems. EC Kun Jin, Xueru Zhang, Mohammad Mahdi Khalili, Parinaz Naghizadeh, Mingyan Liu
2022	J	`jnl`	RewardRating: A Mechanism Design Approach to Improve Rating Systems. Games Iman Vakilinia, Peyman Faizian, Mohammad Mahdi Khalili
2022	—	`conf`	Towards Fair Representation Learning in Knowledge Graph with Stable Adversarial Debiasing. ICDM (Workshops) Yihe Wang, Mohammad Mahdi Khalili, Xiang Zhang
2021	—	`conf`	A Mechanism Design Approach to Solve Ransomware Dilemmas. GameSec Iman Vakilinia, Mohammad Mahdi Khalili, Ming Li
2021	J	`jnl`	Designing Contracts for Trading Private and Heterogeneous Data Using a Biased Differentially Private Algorithm. IEEE Access Mohammad Mahdi Khalili, Xueru Zhang, Mingyan Liu
2021	A*	`conf`	Fair Sequential Selection Using Supervised Learning Models. NeurIPS Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan
2021	J	`jnl`	Fair Sequential Selection Using Supervised Learning Models. CoRR Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan
2021	A*	`conf`	Improving Fairness and Privacy in Selection Problems. AAAI Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan, Somayeh Sojoudi
2021	J	`jnl`	Resource Pooling for Shared Fate: Incentivizing Effort in Interdependent Security Games Through Cross-Investments. IEEE Trans. Control. Netw. Syst. Mohammad Mahdi Khalili, Xueru Zhang, Mingyan Liu
2021	J	`jnl`	RewardRating: A Mechanism Design Approach to Improve Rating Systems. CoRR Iman Vakilinia, Peyman Faizian, Mohammad Mahdi Khalili
2021	—	`conf`	Trading Privacy through Randomized Response. INFOCOM Workshops Mohammad Mahdi Khalili, Iman Vakilinia
2020	C	`conf`	Games on Networks with Community Structure: Existence, Uniqueness and Stability of Equilibria. ACC Kun Jin, Mohammad Mahdi Khalili, Mingyan Liu
2020	J	`jnl`	Improving Fairness and Privacy in Selection Problems. CoRR Mohammad Mahdi Khalili, Xueru Zhang, Mahed Abroshan, Somayeh Sojoudi
2020	J	`jnl`	Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms. IEEE Trans. Inf. Forensics Secur. Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2019	J	`jnl`	A Continuously Updated, Computationally Efficient Stress Recognition Framework Using Electroencephalogram (EEG) by Applying Online Multitask Learning Algorithms (OMTL). IEEE J. Biomed. Health Informatics Houtan Jebelli, Mohammad Mahdi Khalili, Sanghyun Lee
2019	—	`conf`	Contract design for purchasing private data using a biased differentially private algorithm. NetEcon@SIGMETRICS Mohammad Mahdi Khalili, Xueru Zhang, Mingyan Liu
2019	—	`conf`	Effective Premium Discrimination for Designing Cyber Insurance Policies with Rare Losses. GameSec Mohammad Mahdi Khalili, Xueru Zhang, Mingyan Liu
2019	J	`jnl`	Embracing and controlling risk dependency in cyber-insurance policy underwriting. J. Cybersecur. Mohammad Mahdi Khalili, Mingyan Liu, Sasha Romanosky
2019	—	`conf`	Incentivizing effort in interdependent security games using resource pooling. NetEcon@SIGMETRICS Mohammad Mahdi Khalili, Xueru Zhang, Mingyan Liu
2019	J	`jnl`	Long term impact of fair machine learning in sequential decision making: representation disparity and group retention. CoRR Xueru Zhang, Mohammad Mahdi Khalili, Cem Tekin, Mingyan Liu
2019	J	`jnl`	Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms. CoRR Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2018	J	`jnl`	Designing Cyber Insurance Policies: The Role of Pre-Screening and Security Interdependence. IEEE Trans. Inf. Forensics Secur. Mohammad Mahdi Khalili, Parinaz Naghizadeh, Mingyan Liu
2018	A*	`conf`	Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms. ICML Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2018	J	`jnl`	Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms. CoRR Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2018	—	`conf`	Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms. Allerton Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2018	J	`jnl`	Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms. CoRR Xueru Zhang, Mohammad Mahdi Khalili, Mingyan Liu
2017	—	`conf`	Designing Cyber Insurance Policies: Mitigating Moral Hazard Through Security Pre-Screening. GAMENETS Mohammad Mahdi Khalili, Parinaz Naghizadeh, Mingyan Liu
2017	—	`conf`	Designing cyber insurance policies in the presence of security interdependence. NetEcon@EC Mohammad Mahdi Khalili, Parinaz Naghizadeh, Mingyan Liu
2017	—	`conf`	Embracing risk dependency in designing cyber-insurance contracts. Allerton Mohammad Mahdi Khalili, Parinaz Naghizadeh, Mingyan Liu
2015	J	`jnl`	Incentive Design and Market Evolution of Mobile User-Provided Networks. CoRR Mohammad Mahdi Khalili, Lin Gao, Jianwei Huang, Babak Hossein Khalaj
2015	—	`conf`	Incentive design and market evolution of mobile user-provided networks. INFOCOM Workshops Mohammad Mahdi Khalili, Lin Gao, Jianwei Huang, Babak Hossein Khalaj