byzantine robustness 1federated learning 1heterogeneous data 1robust aggregation 1truncated-quadratic loss 1
From the 1 of 17 linked papers with an AI index.
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Enhanced Byzantine-Robust Federated Learning Via Truncated-Quadratic Loss for Heterogeneous Data
Zhi-Yong Wang, Hao Nan Sheng, Werner Stefan +3
The paper proposes a new aggregation rule based on truncated‑quadratic loss to improve Byzantine‑robust federated learning under heterogeneous and non‑convex data, showing theoreti…
cs.LG2026
Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
Yuxuan Yao, Haonan Sheng, Qingsong Lv +11
The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. Howev…
cs.LG2025
AROMA: Autonomous Rank-one Matrix Adaptation
Hao Nan Sheng, Zhi-yong Wang, Mingrui Yang +1
As large language models continue to grow in size, parameter-efficient fine-tuning (PEFT) has become increasingly crucial. While low-rank adaptation (LoRA) offers a solution throug…