用MLP增强通道混合，让循环卷积网络更泛化。
Channel-Wise MLPs Improve the Generalization of Recurrent Convolutional Networks
- 引入门控MLP实现通道间混合，提升模型表达能力。
- 在Re-ARC基准上，新模型在分布内和分布外均显著优于原模型。
- 适合研究神经程序合成与超网络架构的学者参考。
我们研究了通过多层感知机（MLPs）进行通道混合对循环卷积网络泛化能力的影响。具体比较两种结构：DARC（深度感知循环卷积）采用简单循环卷积结构，而DAMP（深度感知多层感知机）在DARC基础上引入门控MLP实现通道混合。基于Re-ARC基准测试，在精确匹配评分标准下，DAMP在分布内和分布外泛化性能均显著优于DARC。结果表明，通过MLP显式实现通道混合，可使循环卷积网络学习到更鲁棒、更具泛化性的计算模式。该发现对神经程序合成具有启示意义，并表明DAMP是超网络方法的理想候选架构。
原文摘要 · Abstract (English)
We investigate the impact of channel-wise mixing via multi-layer perceptrons (MLPs) on the generalization capabilities of recurrent convolutional networks. Specifically, we compare two architectures: DARC (Depth Aware Recurrent Convolution), which employs a simple recurrent convolutional structure, and DAMP (Depth Aware Multi-layer Perceptron), which extends DARC with a gated MLP for channel mixing. Using the Re-ARC benchmark, we find that DAMP significantly outperforms DARC in both in-distribution and out-of-distribution generalization under exact-match grading criteria. These results suggest that explicit channel mixing through MLPs enables recurrent convolutional networks to learn more robust and generalizable computational patterns. Our findings have implications for neural program synthesis and highlight the potential of DAMP as a target architecture for hypernetwork approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。