提出可解释的深度模型χ-net，融合张量网络与神经网络优势。
Compositionality Unlocks Deep Interpretable Models
- 用张量网络结构构建可解释的深层网络
- 在SVHN上发现权重具低秩线性结构
- 适合需要透明性与压缩的模型应用
我们提出χ-net，一种内在可解释的架构，结合张量网络的组合型多线性结构与深度神经网络的表达力和效率。χ-net在保持与基准模型相当精度的同时，通过新型高效对角化算法ODT，在多层SVHN模型中揭示了权重的线性低秩结构，从而实现基于权重的正式可解释性与模型压缩。
原文摘要 · Abstract (English)
We propose $χ$-net, an intrinsically interpretable architecture combining the compositional multilinear structure of tensor networks with the expressivity and efficiency of deep neural networks. $χ$-nets retain equal accuracy compared to their baseline counterparts. Our novel, efficient diagonalisation algorithm, ODT, reveals linear low-rank structure in a multilayer SVHN model. We leverage this toward formal weight-based interpretability and model compression.
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。