arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01615cs.LG
收藏

用于可伸缩集合编码的小批量一致性槽集编码器

Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding

KAIST(韩国科学技术院);AITRICS

Bruno Andreis, Jeffrey Willette, Juho Lee, Sung Ju Hwang

摘要:

大多数现有的集合编码算法都是在隐含的假设下操作的,即所有的集合元素都是可访问的,并且在训练和推理期间有足够的计算和内存资源将集合加载到内存中。然而,当集合太大以至于不可能将所有集合元素加载到内存中时,或者当数据到达流时,这两个假设都失败了。为了解决大规模集合编码中的实际挑战,置换不变性和等变性的一般集合函数约束是不够的。我们引入了一个新的属性称为小批量一致性(MBC),需要大规模的小批量集编码。此外,我们提出了一个可扩展的和有效的注意力为基础的集编码机制,是服从迷你批处理的集,并能够更新集表示数据到达。所提出的方法坚持所需的对称性的不变性和等变性,以及保持MBC的任何分区的输入集。我们进行了广泛的实验,并表明我们的方法是计算效率高,结果在丰富的集合编码表示集结构化数据。

英文摘要:

Most existing set encoding algorithms operate under the implicit assumption that all the set elements are accessible, and that there are ample computational and memory resources to load the set into memory during training and inference. However, both assumptions fail when the set is excessively large such that it is impossible to load all set elements into memory, or when data arrives in a stream. To tackle such practical challenges in large-scale set encoding, the general set-function constraints of permutation invariance and equivariance are not sufficient. We introduce a new property termed Mini-Batch Consistency (MBC) that is required for large scale mini-batch set encoding. Additionally, we present a scalable and efficient attention-based set encoding mechanism that is amenable to mini-batch processing of sets, and capable of updating set representations as data arrives. The proposed method adheres to the required symmetries of invariance and equivariance as well as maintaining MBC for any partition of the input set. We perform extensive experiments and show that our method is computationally efficient and results in rich set encoding representations for set-structured 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。

↑