Salman Avestimehr

Salman Avestimehr

University of Southern California

H-index: 59

North America-United States

About Salman Avestimehr

Salman Avestimehr, With an exceptional h-index of 59 and a recent h-index of 48 (since 2020), a distinguished researcher at University of Southern California, specializes in the field of Information Theory, Machine Learning, Distributed Computing, Secure/Private Learning/Computing.

His recent articles reflect a diverse array of research interests and contributions to the field:

One model to unite them all: Personalized federated learning of multi-contrast MRI synthesis

Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs

Edge Private Graph Neural Networks with Singular Value Perturbation

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

Ethos: Rectifying Language Models in Orthogonal Parameter Space

Coded Computing: A Transformative Framework for Edge Computing

LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning

Salman Avestimehr Information

University

Position

Dean's Professor and Director of -Amazon Center on Trusted AI

Citations(all)

13525

Citations(since 2020)

8753

Cited By

7551

hIndex(all)

59

hIndex(since 2020)

48

i10Index(all)

174

i10Index(since 2020)

127

Email

University Profile Page

University of Southern California

Google Scholar

View Google Scholar Profile

Salman Avestimehr Skills & Research Interests

Information Theory

Machine Learning

Distributed Computing

Secure/Private Learning/Computing

Top articles of Salman Avestimehr

Title

Journal

Author(s)

Publication Date

One model to unite them all: Personalized federated learning of multi-contrast MRI synthesis

Medical Image Analysis

Onat Dalmaz

Muhammad U Mirza

Gokberk Elmas

Muzaffer Ozbey

Salman UH Dar

...

2024/2/23

Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation

arXiv preprint arXiv:2403.17296

Hamza Saleem

Amir Ziashahabi

Muhammad Naveed

Salman Avestimehr

2024/3/26

MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs

arXiv preprint arXiv:2402.11756

Yavuz Faruk Bakman

Duygu Nur Yaldiz

Baturalp Buyukates

Chenyang Tao

Dimitrios Dimitriadis

...

2024/2/19

Edge Private Graph Neural Networks with Singular Value Perturbation

Tingting Tang*

Yue Niu*

Salman Avestimehr

Murali Annavaram

2024

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

Advances in Neural Information Processing Systems

Sara Babakniya

Zalan Fabian

Chaoyang He

Mahdi Soltanolkotabi

Salman Avestimehr

2024/2/13

Ethos: Rectifying Language Models in Orthogonal Parameter Space

Lei Gao*

Yue Niu*

Tingting Tang

Salman Avestimehr

Murali Annavaram

2024

Coded Computing: A Transformative Framework for Edge Computing

Global Communications

Songze Li

A Salman Avestimehr

2024/1

LightVeriFL: A Lightweight and Verifiable Secure Aggregation for Federated Learning

IEEE Journal on Selected Areas in Information Theory

Baturalp Buyukates

Jinhyun So

Hessam Mahdavifar

Salman Avestimehr

2024/4/29

ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys

arXiv preprint arXiv:2403.02352

Yue Niu

Saurav Prakash

Salman Avestimehr

2024/3/1

Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training

IEEE Transactions on Mobile Computing

Sunwoo Lee

Tuo Zhang

Saurav Prakash

Yue Niu

Salman Avestimehr

2024

Renormalization Group flow, Optimal Transport and Diffusion-based Generative Model

arXiv preprint arXiv:2402.17090

Artan Sheshmani

Yi-Zhuang You

Baturalp Buyukates

Amir Ziashahabi

Salman Avestimehr

2024/2/26

Fedmlsecurity: A benchmark for attacks and defenses in federated learning and llms

arXiv preprint arXiv:2306.04959

Shanshan Han

Baturalp Buyukates

Zijian Hu

Han Jin

Weizhao Jin

...

2023/6/8

Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory

arXiv preprint arXiv:2307.00497

Sara Babakniya

Zalan Fabian

Chaoyang He

Mahdi Soltanolkotabi

Salman Avestimehr

2023/7/2

Fedmultimodal: A benchmark for multimodal federated learning

2023 KDD

Tiantian Feng

Digbalay Bose

Tuo Zhang

Rajat Hebbar

Anil Ramakrishna

...

2023/6/15

Performance and Failure Cause Estimation for Machine Learning Systems in the Wild

Xiruo Liu

Furqan Khan

Yue Niu

Pradeep Natarajan

Rinat Khaziev

...

2023/9/21

FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things

arXiv preprint arXiv:2310.00109

Samiul Alam

Tuo Zhang

Tiantian Feng

Hui Shen

Zhichao Cao

...

2023/10

Integral: A Foundational Approach to Label Complexity via Information Theory and Graph Signal Processing

Salman Avestimehr

Antonio Ortega

Mahdi Soltanolkotabi

Ilias Diakonikolas

2023/11/1

Federated analytics: A survey

APSIPA Transactions on Signal and Information Processing

Ahmed Roushdy Elkordy

Yahya H Ezzeldin

Shanshan Han

Shantanu Sharma

Chaoyang He

...

2023/2/2

Secure aggregation in federated learning is not private: Leaking user data at large scale through model modification

arXiv preprint arXiv:2303.12233

Joshua C Zhao

Atul Sharma

Ahmed Roushdy Elkordy

Yahya H Ezzeldin

Salman Avestimehr

...

2023/3/21

Quantifying catastrophic forgetting in continual federated learning

Christophe Dupuy

Jimit Majmudar

Jixuan Wang

Tanya G Roosta

Rahul Gupta

...

2023/6/4

See List of Professors in Salman Avestimehr University(University of Southern California)