Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?

2025-10-01

AI Summary

This work presents the first systematic investigation of catastrophic forgetting in time-series foundation models (TSFMs) under continual learning settings, where sequential fine-tuning across multiple tasks leads to significant performance degradation on previously learned tasks—revealing a critical robustness deficiency. Method: We propose a knowledge retention quantification framework based on synthetically generated periodic data: we construct controllable periodic synthetic datasets and integrate them with zero-shot transfer and sequential fine-tuning paradigms to decouple and independently assess the stability–plasticity trade-off between new-task adaptation and old-knowledge retention. Contribution/Results: Empirical evaluation demonstrates that while existing TSFMs improve performance on new tasks, they suffer severe forgetting across diverse benchmarks—exposing fundamental limitations in their continual learning capability. Our work establishes a reproducible evaluation benchmark and provides essential diagnostic tools to guide the robust evolution of TSFMs.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems
• Natural Language Processing: (Large) Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Time Series Foundation Models (TSFMs) have shown promising zero-shot generalization across diverse forecasting tasks. However, their robustness to continual adaptation remains underexplored. In this work, we investigate the extent to which TSFMs suffer from catastrophic forgetting when fine-tuned sequentially on multiple datasets. Using synthetic datasets designed with varying degrees of periodic structure, we measure the trade-off between adaptation to new data and retention of prior knowledge. Our experiments reveal that, while fine-tuning improves performance on new tasks, it often causes significant degradation on previously learned ones, illustrating a fundamental stability-plasticity dilemma.

Problem

• Investigating catastrophic forgetting in time series foundation models
• Measuring adaptation-retention trade-off during sequential fine-tuning
• Analyzing stability-plasticity dilemma in continual learning scenarios

Innovation

• Evaluating catastrophic forgetting in time series models
• Measuring adaptation-retention trade-off with synthetic datasets
• Demonstrating stability-plasticity dilemma through sequential fine-tuning