8 papers
When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks
Zihao Ding, Jun Huang, Liang Dong
Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back into later rounds. This closed l…
Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
Beining Wu, Zihao Ding, Jun Huang +1
On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and…
SCALE: Sensitivity-Aware Federated Unlearning with Information Freshness Optimization for Mobile Edge Computing
Zihao Ding, Beining Wu, Jun Huang
Federated Unlearning (FU) is emerging as a powerful tool that enables the selective removal of client data to effectively address data contamination and meet strict privacy regulat…
PRISM: Exposing and Resolving Spurious Isolation in Federated Multimodal Continual Learning
Beining Wu, Zihao Ding, Jun Huang
While current federated multimodal continual learning over mixture-of-experts low-rank adaptation (MoE-LoRA) is built on the unverified assumption that routing isolates task-specif…
EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure
Zihao Ding, Beining Wu, Jun Huang
Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint embedding training entangles…
Application-Aware Twin-in-the-Loop Planning for Federated Split Learning over Wireless Edge Networks
Zihao Ding, Beining Wu, Jun Huang +1
We investigate task-success-oriented resource allocation for federated split learning (FSL) at the wireless edge. In this setting, the server must jointly determine bandwidth, tran…