arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14203cs.LGstat.ML
收藏

用于模型服务的神经网络再训练

Neural Network Retraining for Model Serving

Northwestern University(西北大学)

Diego Klabjan, Xiaofeng Zhu

摘要:

我们提出了一个神经网络模型的增量(重新)训练,以应付在模型服务过程中推理的新数据的连续流。因此,这是一个终身学习的过程。我们解决终身再培训的两个挑战:灾难性遗忘和有效的再培训。如果我们将所有过去的和新的数据结合起来,重新训练神经网络模型很容易变得棘手。另一方面,如果只使用新数据重新训练模型,它很容易遭受灾难性遗忘,因此最重要的是要达到正确的平衡。此外,如果我们在每次收集新数据时重新训练模型的所有权重,重新训练往往需要太多的计算资源。为了解决这两个问题,我们提出了一种新的再训练模型,可以选择重要的样本和重要的权重,利用多武装土匪。为了进一步解决遗忘问题,我们提出了一个新的正则化项,专注于突触和神经元的重要性。我们分析了多个数据集,以记录所提出的再培训方法的结果。各种实验表明,我们的再训练方法减轻了灾难性遗忘问题,同时提高模型性能。

英文摘要:

We propose incremental (re)training of a neural network model to cope with a continuous flow of new data in inference during model serving. As such, this is a life-long learning process. We address two challenges of life-long retraining: catastrophic forgetting and efficient retraining. If we combine all past and new data it can easily become intractable to retrain the neural network model. On the other hand, if the model is retrained using only new data, it can easily suffer catastrophic forgetting and thus it is paramount to strike the right balance. Moreover, if we retrain all weights of the model every time new data is collected, retraining tends to require too many computing resources. To solve these two issues, we propose a novel retraining model that can select important samples and important weights utilizing multi-armed bandits. To further address forgetting, we propose a new regularization term focusing on synapse and neuron importance. We analyze multiple datasets to document the outcome of the proposed retraining methods. Various experiments demonstrate that our retraining methodologies mitigate the catastrophic forgetting problem while boosting model performance.

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。

↑