DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification
This work addresses text representation learning for classification tasks, offering a novel NAS approach that is extensible but incremental in its operational scope.
The paper tackles the problem of neural architecture search for text classification by introducing DDNAS, which optimizes architecture search via gradient descent and models latent hierarchical categorization through a discretization layer, achieving consistent outperformance over state-of-the-art NAS methods on eight diverse datasets.
Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture, nor encodes the latent hierarchical categorization behind text input. This paper presents a novel NAS method, Discretized Differentiable Neural Architecture Search (DDNAS), for text representation learning and classification. With the continuous relaxation of architecture representation, DDNAS can use gradient descent to optimize the search. We also propose a novel discretization layer via mutual information maximization, which is imposed on every search node to model the latent hierarchical categorization in text representation. Extensive experiments conducted on eight diverse real datasets exhibit that DDNAS can consistently outperform the state-of-the-art NAS methods. While DDNAS relies on only three basic operations, i.e., convolution, pooling, and none, to be the candidates of NAS building blocks, its promising performance is noticeable and extensible to obtain further improvement by adding more different operations.