Cluster-Guided Label Generation in Extreme Multi-Label Classification
This addresses the challenge of handling tail labels and semantic relations in XMC, offering a novel method that enhances performance for large-scale classification tasks.
The paper tackles the problem of extreme multi-label classification (XMC) by proposing a generation-based approach (XLGen) that uses pre-trained text-to-text models guided by label clusters, which significantly outperforms baselines on tail labels and improves overall performance across four benchmarks.
For extreme multi-label classification (XMC), existing classification-based models poorly perform for tail labels and often ignore the semantic relations among labels, like treating "Wikipedia" and "Wiki" as independent and separate labels. In this paper, we cast XMC as a generation task (XLGen), where we benefit from pre-trained text-to-text models. However, generating labels from the extremely large label space is challenging without any constraints or guidance. We, therefore, propose to guide label generation using label cluster information to hierarchically generate lower-level labels. We also find that frequency-based label ordering and using decoding ensemble methods are critical factors for the improvements in XLGen. XLGen with cluster guidance significantly outperforms the classification and generation baselines on tail labels, and also generally improves the overall performance in four popular XMC benchmarks. In human evaluation, we also find XLGen generates unseen but plausible labels. Our code is now available at https://github.com/alexa/xlgen-eacl-2023.