A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Federated continual learning (FCL) allows distributed autonomous fleets to adapt collaboratively to evolving terrain types across extended mission lifecycles. However, current approaches face several key challenges: 1) they use uniform protection strategies that do not account for the varying sensitivities to forgetting on different network layers; 2) they focus primarily on preventing forgetting during training, without addressing the long-term effects of cumulative drift; and 3) they often depend on idealized simulations that fail to capture the real-world heterogeneity present in distributed fleets. In this paper, we propose a lifecycle-aware dual-timescale FCL framework that incorporates training-time (pre-forgetting) prevention and (post-forgetting) recovery. Under this framework, we design a layer-selective rehearsal strategy that mitigates immediate forgetting during local training, and a rapid knowledge recovery strategy that restores degraded models after long-term cumulative drift. We present a theoretical analysis that characterizes heterogeneous forgetting dynamics and establishes the inevitability of long-term degradation. Our experimental results show that this framework achieves up to 8.3\% mIoU improvement over the strongest federated baseline and up to 31.7\% over conventional fine-tuning. We also deploy the FCL framework on a real-world rover testbed to assess system-level robustness under realistic constraints; the testing results further confirm the effectiveness of our FCL design.
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
PRISM maintains per-expert gradient subspace bases preserved under FedAvg to resolve spurious isolation in federated multimodal continual learning, outperforming 16 baselines with larger gains on longer task sequences.
EASE closes three residual anchors in federated multimodal unlearning using bilateral displacement, cosine-sine decomposition, and forget lock, achieving near-retrain performance on forget and retain data.
TiLP integrates network, training, and task sub-twins into a digital twin and uses receding-horizon cross-entropy planning with actor-critic guidance to jointly optimize resource allocation in federated split learning, improving task success by 9.5 percentage points on robotic tasks.
SCALE introduces a sensitivity-aware federated unlearning method with adaptive sparsification and freshness optimization to achieve better forgetting performance in MEC systems than prior baselines.
citing papers explorer
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
PRISM: Exposing and Resolving Spurious Isolation in Federated Multimodal Continual Learning
PRISM maintains per-expert gradient subspace bases preserved under FedAvg to resolve spurious isolation in federated multimodal continual learning, outperforming 16 baselines with larger gains on longer task sequences.
-
EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure
EASE closes three residual anchors in federated multimodal unlearning using bilateral displacement, cosine-sine decomposition, and forget lock, achieving near-retrain performance on forget and retain data.
-
Application-Aware Twin-in-the-Loop Planning for Federated Split Learning over Wireless Edge Networks
TiLP integrates network, training, and task sub-twins into a digital twin and uses receding-horizon cross-entropy planning with actor-critic guidance to jointly optimize resource allocation in federated split learning, improving task success by 9.5 percentage points on robotic tasks.
-
SCALE: Sensitivity-Aware Federated Unlearning with Information Freshness Optimization for Mobile Edge Computing
SCALE introduces a sensitivity-aware federated unlearning method with adaptive sparsification and freshness optimization to achieve better forgetting performance in MEC systems than prior baselines.