Recent work demonstrated Transformers' ability to efficiently copy strings of
exponential sizes, distinguishing them from other architectures. We present the
Causal Relation Network (CausalRN), an all-MLP sequence modeling architecture
that can match Transformers on the copying task. Extending Relation Networks
(RNs), we implemented key innovations to support autoregressive sequence
modeling while maintaining computational feasibility. We discovered that
exponentially-activated RNs are reducible to linear time complexity, and
pre-activation normalization induces an infinitely growing memory pool, similar
to a KV cache. In ablation study, we found both exponential activation and
pre-activation normalization are indispensable for Transformer-level copying.
Our findings provide new insights into what actually constitutes strong
in-context retrieval.

Causal Relation Network (CausalRN) is an MLP sequence modeling architecture that can match Transformers on the copying task, employing key innovations such as exponentially-activated RNs, pre-activation normalization, and providing insights into strong in-context retrieval.

一个优秀的复制能力的全 MLP 序列建模架构

An All-MLP Sequence Modeling Architecture That Excels at Copying

State space models have shown to be effective at modeling long range
dependencies, specially on sequence classification tasks. In this work we focus
on autoregressive sequence modeling over English books, Github source code and
ArXiv mathematics articles. Based on recent developments around the
effectiveness of gated activation functions, we propose a new layer named Gated
State Space (GSS) and show that it trains significantly faster than the
diagonal version of S4 (i.e. DSS) on TPUs, is fairly competitive with several
well-tuned Transformer-based baselines and exhibits zero-shot generalization to
longer inputs while being straightforward to implement. Finally, we show that
leveraging self-attention to model local dependencies improves the performance
of GSS even further.

本论文介绍了一种基于门控状态空间（GSS）的自回归序列建模方法，该方法使用自注意力来建模局部依赖关系，从而能够有效地处理长距离依赖关系，且在英语书籍、Github 源代码和 ArXiv 数学文章上的实验表明，该方法训练速度明显快于传统方法并且具有零样本推广能力。