arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.01461cs.LGstat.ML
收藏

用于在线模型自适应的标记记忆网络

Labeled Memory Networks for Online Model Adaptation

IIT Bombay(印度理工学院孟买分校)

Shiv Shankar, Sunita Sarawagi

摘要:

用记忆增强神经网络,而不增加训练参数的数量,是一个最近的强大概念,有许多令人兴奋的应用。我们提出了一种设计的记忆增强神经网络(MANN)称为标签记忆网络(LMNs)适合于需要在线适应分类模型的任务。LMN以类作为主键码来组织记忆,记忆作为继常规神经网络之后的第二个提升阶段,从而允许记忆和主网络发挥互补作用。与针对每个实例写入存储器并使用基于LRU的存储器替换的现有MANN不同,LMN仅针对具有非零丢失的实例写入并使用基于标签的存储器替换。我们在各种任务上表现出显着的准确性增益,包括单词建模和少样本学习。在本文中,我们建立了他们的潜力,在线适应一批训练神经网络领域相关的标记数据在部署时。我们表明,LMNs优于其他MANN设计的元学习。我们还发现,它们比最先进的重新调整模型参数的方法更准确,更快,以适应特定领域的标记数据。

英文摘要:

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in classification models. LMNs organize the memory with classes as the primary key.The memory acts as a second boosted stage following a regular neural network thereby allowing the memory and the primary network to play complementary roles. Unlike existing MANNs that write to memory for every instance and use LRU based memory replacement, LMNs write only for instances with non-zero loss and use label-based memory replacement. We demonstrate significant accuracy gains on various tasks including word-modelling and few-shot learning. In this paper, we establish their potential in online adapting a batch trained neural network to domain-relevant labeled data at deployment time. We show that LMNs are better than other MANNs designed for meta-learning. We also found them to be more accurate and faster than state-of-the-art methods of retuning model parameters for adapting to domain-specific labeled data.

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。

↑