arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.07142cs.LGcs.AI
收藏

基于CLAMP的跨域持续学习

Cross-Domain Continual Learning via CLAMP

Nanyang Technological University(南洋理工大学);University of South Australia(南澳大学);SIMTech, A*Star(新加坡科技研究局SIMTech研究院);I2R, A*Star(新加坡科技研究局I2R研究院)

Weiwei Weng, Mahardhika Pratama, Jie Zhang, Chen Chen, Edward Yapp Kien Yee, Ramasamy Savitha

AI总结:

针对跨域持续学习场景下的灾难性遗忘问题,提出整合类别感知对抗域自适应与双评估器引导的CLAMP方法,经理论与实验验证性能优于基准算法至少10%。

摘要:

人工神经网络以其类人认知学习能力著称,但常遭遇众所周知的灾难性遗忘(CF)问题,即神经网络会丧失对先前习得知识的掌握能力。尽管已有大量研究致力于缓解CF问题,但该问题尤其是在复杂多变环境中仍是重大挑战。在持续学习(CL)设置下的跨域自适应场景中,这一挑战更为突出,该场景更具挑战性也更贴近现实,但目前研究尚不充分。为此,本文提出一种跨域持续学习方法,可在无需额外标注成本的情况下,在这类环境中部署单个模型。我们的方法名为多过程持续学习方法(CLAMP),整合了类别感知对抗域自适应策略,以对齐源域和目标域。本文提出一种评估器引导的学习过程,用于调控基础模型的学习流程:为每个样本分配一组权重,控制每个样本的影响以及各损失函数的相互作用,以此平衡稳定性与可塑性的两难困境,从而防止CF问题。第一个评估器聚焦于负迁移问题,拒绝源域中的无关样本;第二个评估器则用于过滤目标域中的噪声伪标签。两个评估器均通过元学习方法训练,训练过程使用随机变换技术和源域中的相似样本。理论分析与大量数值验证表明,在所有实验中,CLAMP的性能均显著优于现有基准算法,优势幅度至少达10%。

英文摘要:

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge. Despite numerous efforts to mitigate CF, it remains the significant challenge particularly in complex changing environments. This challenge is even more pronounced in cross-domain adaptation following the continual learning (CL) setting, which is a more challenging and realistic scenario that is under-explored. To this end, this article proposes a cross-domain CL approach making possible to deploy a single model in such environments without additional labelling costs. Our approach, namely continual learning approach for many processes (CLAMP), integrates a class-aware adversarial domain adaptation strategy to align a source domain and a target domain. An assessor-guided learning process is put forward to navigate the learning process of a base model assigning a set of weights to every sample controlling the influence of every sample and the interactions of each loss function in such a way to balance the stability and plasticity dilemma thus preventing the CF problem. The first assessor focuses on the negative transfer problem rejecting irrelevant samples of the source domain while the second assessor prevents noisy pseudo labels of the target domain. Both assessors are trained in the meta-learning approach using random transformation techniques and similar samples of the source domain. Theoretical analysis and extensive numerical validations demonstrate that CLAMP significantly outperforms established baseline algorithms across all experiments by at least $10\%$ margin.

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。

↑