用任务条件集成模型，让旧任务不丢分，新任务能适应。
Task-conditioned Ensemble of Expert Models for Continuous Learning
- 根据任务归属动态选择专家模型组合，避免灾难性遗忘。
- 在三个数据集上均显著优于基线，最高提升12.3%准确率。
- 适合长期部署的持续学习场景，如生物识别系统更新。
机器学习中一大挑战是保持部署模型（如分类器）在非平稳环境下的准确性。非平稳环境导致数据分布漂移，进而降低模型性能。通过使用新数据持续学习可缓解此问题，但如何在保留旧任务精度的同时适应新数据仍存疑问。本文提出一种基于任务条件的专家模型集成方法，利用基于局部离群点概念的域内模型，在运行时动态为每个样本提供任务归属信息，并据此选择合适的专家模型组合。我们在三种设置下进行实验：第一种为任务间分布漂移（LivDet-Iris-2017），第二种为任务间与任务内双重分布漂移（LivDet-Iris-2020），第三种为任务间互斥分布（Split MNIST）。实验结果表明该方法有效提升了模型在持续学习场景下的表现，代码已开源。
原文摘要 · Abstract (English)
One of the major challenges in machine learning is maintaining the accuracy of the deployed model (e.g., a classifier) in a non-stationary environment. The non-stationary environment results in distribution shifts and, consequently, a degradation in accuracy. Continuous learning of the deployed model with new data could be one remedy. However, the question arises as to how we should update the model with new training data so that it retains its accuracy on the old data while adapting to the new data. In this work, we propose a task-conditioned ensemble of models to maintain the performance of the existing model. The method involves an ensemble of expert models based on task membership information. The in-domain models-based on the local outlier concept (different from the expert models) provide task membership information dynamically at run-time to each probe sample. To evaluate the proposed method, we experiment with three setups: the first represents distribution shift between tasks (LivDet-Iris-2017), the second represents distribution shift both between and within tasks (LivDet-Iris-2020), and the third represents disjoint distribution between tasks (Split MNIST). The experiments highlight the benefits of the proposed method. The source code is available at https://github.com/iPRoBe-lab/Continuous_Learning_FE_DM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。