Sara Babakniya

12 papers A* 1Journal 11

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Clustering and Median Aggregation Improve Differentially Private Inference. CoRR Kareem Amin, Salman Avestimehr, Sara Babakniya, Alex Bie, Weiwei Kong, Natalia Ponomareva, Umar Syed
2025	J	`jnl`	Escaping Collapse: The Strength of Weak Data for Large Language Model Training. CoRR Kareem Amin, Sara Babakniya, Alex Bie, Weiwei Kong, Umar Syed, Sergei Vassilvitskii
2025	J	`jnl`	Supervised Learning for Analog and RF Circuit Design: Benchmarks and Comparative Insights. CoRR Asal Mehradfar, Xuzhe Zhao, Yue Niu, Sara Babakniya, Mahdi Alesheikh, Hamidreza Aghasi, Salman Avestimehr
2024	J	`jnl`	AICircuit: A Multi-Level Dataset and Benchmark for AI-Driven Analog Integrated Circuit Design. CoRR Asal Mehradfar, Xuzhe Zhao, Yue Niu, Sara Babakniya, Mahdi Alesheikh, Hamidreza Aghasi, Salman Avestimehr
2023	A*	`conf`	A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks. NeurIPS Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr
2023	J	`jnl`	A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks. CoRR Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr
2023	J	`jnl`	Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory. CoRR Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr
2023	J	`jnl`	Revisiting Sparsity Hunting in Federated Learning: Why does Sparsity Consensus Matter? Trans. Mach. Learn. Res. Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr
2023	J	`jnl`	SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models. CoRR Sara Babakniya, Ahmed Roushdy Elkordy, Yahya H. Ezzeldin, Qingfeng Liu, Kee-Bong Song, Mostafa El-Khamy, Salman Avestimehr
2022	J	`jnl`	Defending against Poisoning Backdoor Attacks on Federated Meta-learning. ACM Trans. Intell. Syst. Technol. Chien-Lun Chen, Sara Babakniya, Marco Paolieri, Leana Golubchik
2022	J	`jnl`	Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge. CoRR Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr
2021	J	`jnl`	Deep-n-Cheap: An Automated Efficient and Extensible Search Framework for Cost-Effective Deep Learning. SN Comput. Sci. Sourya Dey, Sara Babakniya, Saikrishna C. Kanala, Marco Paolieri, Leana Golubchik, Peter A. Beerel, Keith M. Chugg