面向在线持续学习的基于元更新的样本权重估计
Sample Weight Estimation Using Meta-Updates for Online Continual Learning
AI总结：
针对在线持续学习中样本权重分配未充分优化的问题，提出基于内更新与元更新机制的OMSI策略，通过估计小批次样本权重优化模型，在带噪数据流和标准基准中均取得更优效果，推动自适应持续学习研究。
摘要：
损失函数在优化学习系统性能方面发挥着重要作用，其一个关键方面是损失计算过程中为小批次内的样本分配权重。在持续学习（CL）语境下，现有大多数策略在计算损失值时均统一处理样本，即为每个样本分配相等权重。尽管该方法在部分标准基准中有效，但其最优效果（尤其是在更复杂场景下）仍未得到充分探索，这在“野外”训练（例如借助参考模型自动标注的自训练）中尤为关键。本文提出了样本重要性在线元学习（OMSI）策略，通过内更新与元更新机制，为在线持续学习流中的小批次近似估计样本权重。该策略首先估计小批次中每个样本的权重参数，再使用调整后的样本权重更新模型。我们在两种不同的实验设置下评估OMSI：首先，证明OMSI在受控的带噪标签数据流中同时提升了学习精度和保留精度；随后，在三个标准基准中测试该策略，并将其与其他流行的基于回放的策略进行对比。本研究旨在推动自适应持续学习领域的持续探索。
英文摘要：
The loss function plays an important role in optimizing the performance of a learning system. A crucial aspect of the loss function is the assignment of sample weights within a mini-batch during loss computation. In the context of continual learning (CL), most existing strategies uniformly treat samples when calculating the loss value, thereby assigning equal weights to each sample. While this approach can be effective in certain standard benchmarks, its optimal effectiveness, particularly in more complex scenarios, remains underexplored. This is particularly pertinent in training "in the wild," such as with self-training, where labeling is automated using a reference model. This paper introduces the Online Meta-learning for Sample Importance (OMSI) strategy that approximates sample weights for a mini-batch in an online CL stream using an inner- and meta-update mechanism. This is done by first estimating sample weight parameters for each sample in the mini-batch, then, updating the model with the adapted sample weights. We evaluate OMSI in two distinct experimental settings. First, we show that OMSI enhances both learning and retained accuracy in a controlled noisy-labeled data stream. Then, we test the strategy in three standard benchmarks and compare it with other popular replay-based strategies. This research aims to foster the ongoing exploration in the area of self-adaptive CL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
