Learning Architectures from an Extended Search Space for Language Modeling

by   Yinqiao Li, et al.

Neural architecture search (NAS) has advanced significantly in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell. In this paper, we extend the search space of NAS. In particular, we present a general approach to learn both intra-cell and inter-cell architectures (call it ESS). For a better search result, we design a joint learning method to perform intra-cell and inter-cell NAS simultaneously. We implement our model in a differentiable architecture search system. For recurrent neural language modeling, it outperforms a strong baseline significantly on the PTB and WikiText data, with a new state-of-the-art on PTB. Moreover, the learned architectures show good transferability to other systems. E.g., they improve state-of-the-art systems on the CoNLL and WNUT named entity recognition (NER) tasks and CoNLL chunking task, indicating a promising line of research on large-scale pre-learned architectures.


page 1

page 2

page 3

page 4


Neural Architecture Search of SPD Manifold Networks

In this paper, we propose a new neural architecture search (NAS) problem...

Understanding Architectures Learnt by Cell-based Neural Architecture Search

Neural architecture search (NAS) generates architectures automatically f...

WeNet: Weighted Networks for Recurrent Network Architecture Search

In recent years, there has been increasing demand for automatic architec...

RankNAS: Efficient Neural Architecture Search by Pairwise Ranking

This paper addresses the efficiency challenge of Neural Architecture Sea...

Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR

Neural architecture search (NAS) has been successfully applied to tasks ...

Dynamic Cell Structure via Recursive-Recurrent Neural Networks

In a recurrent setting, conventional approaches to neural architecture s...

SpiderNet: Hybrid Differentiable-Evolutionary Architecture Search via Train-Free Metrics

Neural Architecture Search (NAS) algorithms are intended to remove the b...