arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.04983cs.CLcs.LGstat.ML
收藏

理解词嵌入的下游不稳定性

Understanding the Downstream Instability of Word Embeddings

Stanford University(斯坦福大学);SambaNova Systems(桑巴诺瓦系统公司)

Megan Leszczynski, Avner May, Jian Zhang, Sen Wu, Christopher R. Aberger, Christopher Ré

摘要:

许多工业机器学习(ML)系统需要频繁的再培训,以跟上不断变化的数据。这种再训练加剧了ML系统今天面临的一个巨大挑战:模型训练不稳定,即,训练数据中的小的变化可以引起模型预测中的显著变化。在本文中,我们致力于深入了解这种不稳定性,重点关注现代自然语言处理(NLP)管道的核心构建块-预训练的词嵌入-如何影响下游NLP模型的不稳定性。我们首先经验性地揭示了稳定性和内存之间的权衡:将嵌入内存增加2倍可以将由于训练数据的微小变化而导致的预测不一致减少5%至37%(相对)。为了从理论上解释这种权衡,我们引入了一个新的嵌入不稳定性的措施-本征空间不稳定性措施-我们证明界的下游预测的变化引入的词嵌入的分歧。实际上,我们证明了特征空间不稳定性测度可以是一种具有成本效益的方法来选择嵌入参数,以最大限度地减少不稳定性,而无需训练下游模型,优于其他嵌入距离测度,并与基于最近邻的测度竞争。最后,我们证明了所观察到的稳定性-记忆权衡也扩展到其他类型的嵌入,包括知识图谱和上下文词嵌入。

英文摘要:

Many industrial machine learning (ML) systems require frequent retraining to keep up-to-date with constantly changing data. This retraining exacerbates a large challenge facing ML systems today: model training is unstable, i.e., small changes in training data can cause significant changes in the model's predictions. In this paper, we work on developing a deeper understanding of this instability, with a focus on how a core building block of modern natural language processing (NLP) pipelines---pre-trained word embeddings---affects the instability of downstream NLP models. We first empirically reveal a tradeoff between stability and memory: increasing the embedding memory 2x can reduce the disagreement in predictions due to small changes in training data by 5% to 37% (relative). To theoretically explain this tradeoff, we introduce a new measure of embedding instability---the eigenspace instability measure---which we prove bounds the disagreement in downstream predictions introduced by the change in word embeddings. Practically, we show that the eigenspace instability measure can be a cost-effective way to choose embedding parameters to minimize instability without training downstream models, outperforming other embedding distance measures and performing competitively with a nearest neighbor-based measure. Finally, we demonstrate that the observed stability-memory tradeoffs extend to other types of embeddings as well, including knowledge graph and contextual word embeddings.

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。

↑