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 2410.13166cs.LGcs.AIcs.CL
收藏

一种进化的通用Transformer记忆体

An Evolved Universal Transformer Memory

Sakana AI

Edoardo Cetin, Qi Sun, Tianyu Zhao, Yujin Tang

AI总结:

针对现代基础模型成本与性能的权衡问题,提出可进化的神经注意力记忆模型(NAMMs),通过学习记忆管理网络提升Transformer性能与效率,实现跨模态零样本迁移及多任务显著优化。

摘要:

现有方法通过手工设计的规则丢弃现代基础模型上下文的特定部分,以抵消其不断上升的成本,同时试图保留原始性能。我们利用神经注意力记忆模型(NAMMs)克服这一权衡,引入一个用于记忆管理的学习网络,以同时提高Transformer的性能和效率。我们在预训练Transformer之上进化NAMMs,为各层和注意力头提供不同的潜在上下文,聚焦于最相关的信息。NAMMs可普遍应用于任何使用自注意力的模型,因为它们仅以生成的注意力矩阵中的值为条件。在一小部分问题上学习NAMMs后,我们在多个长上下文基准测试中实现了显著的性能提升,同时将模型的输入上下文削减至原始大小的一小部分。我们表明,我们的条件设定的通用性使仅在语言上训练的NAMMs能够零样本迁移到全新的Transformer架构,甚至跨输入模态,其优势延伸到视觉和强化学习领域。

英文摘要:

Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable to any model using self-attention as they condition exclusively on the values in the produced attention matrices. Learning NAMMs on a small set of problems, we achieve substantial performance improvements across multiple long-context benchmarks while cutting the model's input contexts up to a fraction of the original sizes. We show the generality of our conditioning enables zero-shot transfer of NAMMs trained only on language to entirely new transformer architectures even across input modalities, with their benefits carrying over to vision and reinforcement learning.

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。

↑