---
title: "Mitigating Catastrophic Forgetting in Task-Free Federated Continual Forecasting via Two-Tier Replay under Concept Drift"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.01098v1"
permalink: "https://feed.astralor.com/items/itm_43efa6cc8f7f45cd6dad9a78"
published: "2026-10-31T16:39:09.000Z"
score: 58
channel: "ai"
tags: ["Mitigating Catastrophic Forgetting","Task-Free Federated Continual","Forecasting","Two-Tier Replay","Concept Drift Federated","Federated","RMSE"]
---

# Mitigating Catastrophic Forgetting in Task-Free Federated Continual Forecasting via Two-Tier Replay under Concept Drift

## At a glance

Federated time-series forecasting is increasingly important in applications where temporal data are distributed across privacy-sensitive clients, such as environmental monitoring, smart cities, and industrial sensing. A…

## Key points

- Federated time-series forecasting is increasingly important in applications where temporal data are distributed across privacy-sensitive clients, such as environmental monitoring, smart cities, and industrial sensing.
- A central limitation of current continual-learning protocols is that they usually assume predefined task boundaries, whereas deployed forecasting systems receive an uninterrupted stream and must decide autonomously when…
- This paper addresses catastrophic forgetting in task-free federated forecasting under concept drift.

## Full text

Federated time-series forecasting is increasingly important in applications where temporal data are distributed across privacy-sensitive clients, such as environmental monitoring, smart cities, and industrial sensing. A central limitation of current continual-learning protocols is that they usually assume predefined task boundaries, whereas deployed forecasting systems receive an uninterrupted stream and must decide autonomously when adaptation is necessary. This paper addresses catastrophic forgetting in task-free federated forecasting under concept drift. We introduce a drift-aware continual-learning protocol in which each client monitors prediction-window RMSE, calibrates a robust median threshold from the offline base period, and triggers adaptation only after persistent degradation. To mitigate forgetting, we propose a TwoTierReplay mechanism that separates fixed offline representative memory from online memory. The offline tier preserves long-term knowledge learned during the base phase, while the online tier captures recent distributional changes after drift. Experiments on the Beijing Multi-Site Air- Quality dataset with 12 clients, three forecasting targets, and three horizons show that TwoTierReplay achieves the best stability-plasticity score in all nine target-horizon configurations. It improves over the strongest baseline by approximately 11.4%. These results suggest that explicit temporal structuring of replay memory is a practical and effective mechanism for task-free federated continual forecasting.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_43efa6cc8f7f45cd6dad9a78