Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Faithful and Fast Influence Function via Advanced Sampling
Jungyeon Koh, Hyeonsu Lyu, Jonggyu Jang +1
How can we explain the influence of training data on black-box models? Influence functions (IFs) offer a post-hoc solution by utilizing gradients and Hessians. However, computing t…
cs.LG2024
Fed-ZOE: Communication-Efficient Over-the-Air Federated Learning via Zeroth-Order Estimation
Jonggyu Jang, Hyeonsu Lyu, David J. Love +1
As 6G and beyond networks grow increasingly complex and interconnected, federated learning (FL) emerges as an indispensable paradigm for securely and efficiently leveraging decentr…
cs.LG2024
Deeper Understanding of Black-box Predictions via Generalized Influence Functions
Hyeonsu Lyu, Jonggyu Jang, Sehyun Ryu +1
Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect t…