Random Amalgamation of Adapters for Flatter Loss Landscapes: Towards Class-Incremental Learning with Better Stability

Class-incremental learning (CIL) enables models to continuously learn from streaming data while mitigating catastrophic forgetting of prior knowledge. Our research reveals that the CIL performance of pre-trained models (PTMs) varies significantly across different datasets, a phenomenon underexplored in existing studies. Through visualization, we observe that flatter loss landscapes correlate with superior CIL performance. This insight motivates us to enhance PTMs' CIL capability by promoting loss landscapes' flatness. Initially, we propose independently optimizing multiple adapter branches to equip PTMs with diverse learnable parameters, thereby improving stability during parameter updates. However, given computational and memory constraints, the number of adapters a PTM can accommodate is limited. To address this, we introduce a training strategy with randomized adapter amalgamation (RAA), compelling the model to maintain low loss across a broader and more continuous parameter space, significantly enhancing flatness. Furthermore, we refine existing sharpness-aware minimization techniques to further optimize the loss landscapes. Our extensive experiments and visualization results validate the efficacy of the method, resulting in the state-of-the-art (SOTA) performance.