Toward a Holistic Approach to Continual Model Merging
This addresses scalability and efficiency issues in continual learning for AI systems that need to adapt to new tasks without forgetting previous ones, though it appears incremental as it builds on existing model merging techniques.
The paper tackles the problem of catastrophic forgetting in continual learning by proposing a holistic framework for continual model merging that operates at three stages (pre-merging, during merging, and post-merging) without accessing old data. The method achieves competitive performance on standard benchmarks while maintaining constant memory constraints.
We present a holistic framework for continual model merging that intervenes at three critical stages: pre-merging, during merging, and post-merging-to address two fundamental challenges in continual learning. In particular, conventional approaches either maintain a growing list of per-domain task vectors, leading to scalability issues or rely solely on weight-space merging when old data is inaccessible, thereby losing crucial functional information. Our method overcomes these limitations by first fine-tuning the main model within its tangent space on domain-specific data; this linearization amplifies per-task weight disentanglement, effectively mitigating across-task interference. During merging, we leverage functional information from available optimizer states beyond mere parameter averages to avoid the need to revisit old data. Finally, a post-merging correction aligns the representation discrepancy between pre- and post-merged models, reducing bias and enhancing overall performance-all while operating under constant memory constraints without accessing historical data. Extensive experiments on standard class-incremental and domain-incremental benchmarks demonstrate that our approach not only achieves competitive performance but also provides a scalable and efficient solution to the catastrophic forgetting problem.